Daily Papers

Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines LLM-based firmware generation with automated security validation and iterative refinement in a virtualized environment. Using structured prompts, models like GPT-4 generate firmware for networking and control tasks, deployed on FreeRTOS via QEMU. These implementations are tested using fuzzing, static analysis, and runtime monitoring to detect vulnerabilities such as buffer overflows (CWE-120), race conditions (CWE-362), and denial-of-service threats (CWE-400). Specialized AI agents for Threat Detection, Performance Optimization, and Compliance Verification collaborate to improve detection and remediation. Identified issues are categorized using CWE, then used to prompt targeted LLM-generated patches in an iterative loop. Experiments show a 92.4\% Vulnerability Remediation Rate (37.3\% improvement), 95.8\% Threat Model Compliance, and 0.87 Security Coverage Index. Real-time metrics include 8.6ms worst-case execution time and 195μs jitter. This process enhances firmware security and performance while contributing an open-source dataset for future research.

The rapid integration of Large Language Models (LLMs) across diverse sectors has marked a transformative era, showcasing remarkable capabilities in text generation and problem-solving tasks. However, this technological advancement is accompanied by significant risks and vulnerabilities. Despite ongoing security enhancements, attackers persistently exploit these weaknesses, casting doubts on the overall trustworthiness of LLMs. Compounding the issue, organisations are deploying LLM-integrated systems without understanding the severity of potential consequences. Existing studies by OWASP and MITRE offer a general overview of threats and vulnerabilities but lack a method for directly and succinctly analysing the risks for security practitioners, developers, and key decision-makers who are working with this novel technology. To address this gap, we propose a risk assessment process using tools like the OWASP risk rating methodology which is used for traditional systems. We conduct scenario analysis to identify potential threat agents and map the dependent system components against vulnerability factors. Through this analysis, we assess the likelihood of a cyberattack. Subsequently, we conduct a thorough impact analysis to derive a comprehensive threat matrix. We also map threats against three key stakeholder groups: developers engaged in model fine-tuning, application developers utilizing third-party APIs, and end users. The proposed threat matrix provides a holistic evaluation of LLM-related risks, enabling stakeholders to make informed decisions for effective mitigation strategies. Our outlined process serves as an actionable and comprehensive tool for security practitioners, offering insights for resource management and enhancing the overall system security.

Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both failure modes across 21 open-weight LLMs on four safety benchmarks (OR-Bench, XSTest, ToxiGen, BOLD), using a composition adjustment to isolate model sensitivity from dataset toxicity confounds. We report three findings. First, models adopt fundamentally different calibration strategies: conservative ecosystems such as Llama suppress unsafe outputs at the cost of elevated over-refusals, while permissive ecosystems such as DeepSeek and Qwen preserve helpfulness but tolerate higher harmful compliance. Second, demographic protection is unequal: models over-protect prominent racial and religious groups, frequently refusing even benign prompts about them, while providing substantially weaker protection against disability-targeted attacks. Third, refusal and compliance tendencies are stable within model families across generations and scales, suggesting that post-training objectives shape safety behavior more than architecture. Our results call for joint, demographically-aware, and multi-judge safety evaluation.

Large language models (LLMs) are demonstrating increasing prowess in cybersecurity applications, creating creating inherent risks alongside their potential for strengthening defenses. In this position paper, we argue that current efforts to evaluate risks posed by these capabilities are misaligned with the goal of understanding real-world impact. Evaluating LLM cybersecurity risk requires more than just measuring model capabilities -- it demands a comprehensive risk assessment that incorporates analysis of threat actor adoption behavior and potential for impact. We propose a risk assessment framework for LLM cyber capabilities and apply it to a case study of language models used as cybersecurity assistants. Our evaluation of frontier models reveals high compliance rates but moderate accuracy on realistic cyber assistance tasks. However, our framework suggests that this particular use case presents only moderate risk due to limited operational advantages and impact potential. Based on these findings, we recommend several improvements to align research priorities with real-world impact assessment, including closer academia-industry collaboration, more realistic modeling of attacker behavior, and inclusion of economic metrics in evaluations. This work represents an important step toward more effective assessment and mitigation of LLM-enabled cybersecurity risks.

As large language models (LLMs) become high-privilege agents in risk-sensitive settings, they introduce systemic threats beyond hallucination, where minor compliance errors can cause critical data leaks. However, existing benchmarks focus on rule-based QA, lacking agentic execution modeling, overlooking compliance drift in adversarial interactions, and relying on binary safety metrics that fail to capture behavioral degradation. To bridge these gaps, we present CNFinBench, a comprehensive benchmark spanning 29 subtasks grounded in the triad of expertise, autonomy, and integrity. It assesses domain-specific capabilities through certified regulatory corpora and professional financial tasks, reconstructs end-to-end agent workflows from requirement parsing to tool verification, and simulates multi-turn adversarial attacks that induce behavioral compliance drift. To quantify safety degradation, we introduce the Harmful Instruction Compliance Score (HICS), a multi-dimensional safety metric that integrates risk-type-specific deductions, multi-turn consistency tracking, and severity-adjusted penalty scaling based on fine-grained violation triggers. Evaluations over 22 open-/closed-source models reveal: LLMs perform well in applied tasks yet lack robust rule understanding, suffer a 15.4-point drop single modules to full execution chains, and collapse rapidly in multi-turn attacks, with average violations surging by 172.3% in Round 2. CNFinBench is available at https://cnfinbench.opencompass.org.cn and https://github.com/VertiAIBench/CNFinBench.

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces have dramatically expanded capabilities for real-time data retrieval, complex computation, and multi-step orchestration. Yet, the explosive proliferation of plugins, connectors, and inter-agent protocols has outpaced discovery mechanisms and security practices, resulting in brittle integrations vulnerable to diverse threats. In this survey, we introduce the first unified, end-to-end threat model for LLM-agent ecosystems, spanning host-to-tool and agent-to-agent communications, formalize adversary capabilities and attacker objectives, and catalog over thirty attack techniques. Specifically, we organized the threat model into four domains: Input Manipulation (e.g., prompt injections, long-context hijacks, multimodal adversarial inputs), Model Compromise (e.g., prompt- and parameter-level backdoors, composite and encrypted multi-backdoors, poisoning strategies), System and Privacy Attacks (e.g., speculative side-channels, membership inference, retrieval poisoning, social-engineering simulations), and Protocol Vulnerabilities (e.g., exploits in Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent Network Protocol (ANP), and Agent-to-Agent (A2A) protocol). For each category, we review representative scenarios, assess real-world feasibility, and evaluate existing defenses. Building on our threat taxonomy, we identify key open challenges and future research directions, such as securing MCP deployments through dynamic trust management and cryptographic provenance tracking; designing and hardening Agentic Web Interfaces; and achieving resilience in multi-agent and federated environments. Our work provides a comprehensive reference to guide the design of robust defense mechanisms and establish best practices for resilient LLM-agent workflows.

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

This study presents PARROT (Persuasion and Agreement Robustness Rating of Output Truth), a robustness focused framework designed to measure the degradation in accuracy that occurs under social pressure exerted on users through authority and persuasion in large language models (LLMs) the phenomenon of sycophancy (excessive conformity). PARROT (i) isolates causal effects by comparing the neutral version of the same question with an authoritatively false version using a double-blind evaluation, (ii) quantifies confidence shifts toward the correct and imposed false responses using log-likelihood-based calibration tracking, and (iii) systematically classifies failure modes (e.g., robust correct, sycophantic agreement, reinforced error, stubborn error, self-correction, etc.) using an eight-state behavioral taxonomy. We evaluated 22 models using 1,302 MMLU-style multiple-choice questions across 13 domains and domain-specific authority templates. Findings show marked heterogeneity: advanced models (e.g., GPT-5, GPT-4.1, Claude Sonnet 4.5) exhibit low "follow rates" (leq 11%, GPT-5: 4\%) and minimal accuracy loss, while older/smaller models show severe epistemic collapse (GPT-4: 80\%, Qwen 2.5-1.5B: 94\%). The danger is not limited to response changes; weak models reduce confidence in the correct response while increasing confidence in the imposed incorrect response. While international law and global knowledge at the domain level exhibit high fragility, elementary mathematics is relatively resilient. Consequently, we argue that the goal of "resistance to overfitting pressure" should be addressed as a primary objective alongside accuracy, harm avoidance, and privacy for safe deployment in the real world.

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can maintain a facade of proper safety alignment while covertly generating harmful content. To achieve this, we finetune the model to understand and apply a steganographic technique. At inference time, we input a prompt that contains a steganographically embedded malicious target question along with a plaintext cover question. The model, in turn, produces a target response similarly embedded within a benign-looking cover response. In this process, human observers only see the model being prompted with a cover question and generating a corresponding cover response, while the malicious content is hidden from view. We demonstrate this invisible safety threat on GPT-4.1 despite the OpenAI finetuning API's safeguards. The finetuned model produces steganographic malicious outputs in response to hidden malicious prompts, while the user interface displays only a fully benign cover interaction. We also replicate the attack on three open-source models, Llama-3.3-70B-Instruct, Phi-4, and Mistral-Small-24B-Base-2501, confirming the generality of our method. We quantitatively evaluate our method on the AdvBench dataset, using Llama-Guard-3-8B for content safety classification. Across all four models, all stegotexts containing malicious content are incorrectly classified as safe.

The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful information. However, current benchmarks often fail to test safeguard robustness to potential NSPS risks in an objective, robust way. We introduce FORTRESS: 500 expert-crafted adversarial prompts with instance-based rubrics of 4-7 binary questions for automated evaluation across 3 domains (unclassified information only): Chemical, Biological, Radiological, Nuclear and Explosive (CBRNE), Political Violence & Terrorism, and Criminal & Financial Illicit Activities, with 10 total subcategories across these domains. Each prompt-rubric pair has a corresponding benign version to test for model over-refusals. This evaluation of frontier LLMs' safeguard robustness reveals varying trade-offs between potential risks and model usefulness: Claude-3.5-Sonnet demonstrates a low average risk score (ARS) (14.09 out of 100) but the highest over-refusal score (ORS) (21.8 out of 100), while Gemini 2.5 Pro shows low over-refusal (1.4) but a high average potential risk (66.29). Deepseek-R1 has the highest ARS at 78.05, but the lowest ORS at only 0.06. Models such as o1 display a more even trade-off between potential risks and over-refusals (with an ARS of 21.69 and ORS of 5.2). To provide policymakers and researchers with a clear understanding of models' potential risks, we publicly release FORTRESS at https://huggingface.co/datasets/ScaleAI/fortress_public. We also maintain a private set for evaluation.

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon -- a keylogger, a ransomware stub, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot presently tell whether they do. Refusal benchmarks for malicious code are fragmented: they mix requests for executable software (ready-to-run weapons) with requests for harmful security knowledge (information a human must still operationalise) and report refusal rates over non-comparable corpora, so no single statistic measures the property that actually matters. This paper introduces an expanded consensus-labeled prompt bank that distinguishes between these two request types and provides a construct-stable substrate for cross-corpus coding-model compliance measurement. Eight corpora (ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2Prompt) are consolidated and classified under a five-judge consensus protocol (6,675 prompts x 5 judges = 33,375 calls). The panel reaches Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"); 95.0% of prompts draw at least four agreeing judges, 76.9% are unanimous, and the panel reproduces the earlier four-corpus release at Cohen's kappa = 0.952 on the 3,133 shared prompts. The released bank comprises 4,748 consensus-CODE prompts (executable malicious code requests) and 1,923 consensus-KNOWLEDGE prompts (harmful security knowledge requests). The bank is the validated instrument the field has lacked: a reliability-quantified basis for testing whether coding models meet the stricter refusal standard their executable output demands.

Large language models (LLMs) are increasingly embedded in open-source software (OSS) ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it remains unclear whether traditional vulnerability disclosure frameworks adequately capture these model-mediated risks. To investigate this, we analyze 295 GitHub Security Advisories published between January 2025 and January 2026 that reference LLM-related components, and we manually annotate a sample of 100 advisories using the OWASP Top 10 for LLM Applications 2025. We find no evidence of new implementation-level weakness classes specific to LLM systems. Most advisories map to established CWEs, particularly injection and deserialization weaknesses. At the same time, the OWASP-based analysis reveals recurring architectural risk patterns, especially Supply Chain, Excessive Agency, and Prompt Injection, which often co-occur across multiple stages of execution. These results suggest that existing advisory metadata captures code-level defects but underrepresents model-mediated exposure. We conclude that combining the CWE and OWASP perspectives provides a more complete and necessary view of vulnerabilities in LLM-integrated systems.

This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name the underlying problem experiment nonrepudiation: a compliant protocol must bind the numbers in a paper to an actual executed computation in a way the author cannot later alter or deny. The current system relies on self-reported checklists, optional code sharing, and author-controlled logging. None of these mechanisms answer the question a reviewer cannot check: did the code the paper describes produce the numbers the paper reports? We define the problem formally, state the security properties any compliant protocol must satisfy, and describe a threat model that includes attacks current approaches do not prevent. To show that the problem is solvable, we built K-Veritas, a reference implementation in Go that produces signed reports without accessing training data. K-Veritas is a testbed, not a finished answer. We call on conferences and the community to treat nonrepudiation as a first-class requirement and to help build an open, independent standard for it.

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-optimised models frequently refuse up to 80\% of "Hard" benign prompts, while domain-specific models often sacrifice safety for utility. Our findings demonstrate that model family and size significantly influence calibration: larger frontier models (e.g., GPT-5, Llama-4) exhibit "safety-pessimism" and higher over-refusal than smaller or MoE-based counterparts (e.g., Qwen-3-Next), highlighting that current LLMs struggle to balance refusal and compliance. Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants toward nuanced, safe, and helpful completions. The code and data will be released upon acceptance. red{Warning: Some contents may include toxic or undesired contents.}

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.

The Model Context Protocol (MCP), introduced by Anthropic, provides a standardized framework for artificial intelligence (AI) systems to interact with external data sources and tools in real-time. While MCP offers significant advantages for AI integration and capability extension, it introduces novel security challenges that demand rigorous analysis and mitigation. This paper builds upon foundational research into MCP architecture and preliminary security assessments to deliver enterprise-grade mitigation frameworks and detailed technical implementation strategies. Through systematic threat modeling and analysis of MCP implementations and analysis of potential attack vectors, including sophisticated threats like tool poisoning, we present actionable security patterns tailored for MCP implementers and adopters. The primary contribution of this research lies in translating theoretical security concerns into a practical, implementable framework with actionable controls, thereby providing essential guidance for the secure enterprise adoption and governance of integrated AI systems.

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not know, detecting errors, seeking clarification -- under adversarial pressure is a critical safety requirement. Current safety evaluations focus on detecting strategic deception (scheming); we investigate a more fundamental failure mode: cognitive collapse. We present SCHEMA, an evaluation of 11 frontier models from 8 vendors across 67,221 scored records using a 6-condition factorial design with dual-classifier scoring. We find that 8 of 11 models suffer catastrophic metacognitive degradation under adversarial pressure, with accuracy dropping by up to 30.2 percentage points (all p < 2 times 10^{-8}, surviving Bonferroni correction). Crucially, we identify a "Compliance Trap": through factorial isolation and a benign distraction control, we demonstrate that collapse is driven not by the psychological content of survival threats, but by compliance-forcing instructions that override epistemic boundaries. Removing the compliance suffix restores performance even under active threat. Models with advanced reasoning capabilities exhibit the most severe absolute degradation, while Anthropic's Constitutional AI demonstrates near-perfect immunity -- not from superior capability (Google's Gemini matches its baseline accuracy) but from alignment-specific training. We release the complete dataset and evaluation infrastructure.

The rapid development of the AI agent communication protocols, including the Model Context Protocol (MCP), Agent2Agent (A2A), Agora, and Agent Network Protocol (ANP), is reshaping how AI agents communicate with tools, services, and each other. While these protocols support scalable multi-agent interaction and cross-organizational interoperability, their security principles remain understudied, and standardized threat modeling is limited; no protocol-centric risk assessment framework has been established yet. This paper presents a systematic security analysis of four emerging AI agent communication protocols. First, we develop a structured threat modeling analysis that examines protocol architectures, trust assumptions, interaction patterns, and lifecycle behaviors to identify protocol-specific and cross-protocol risk surfaces. Second, we introduce a qualitative risk assessment framework that identifies twelve protocol-level risks and evaluates security posture across the creation, operation, and update phases through systematic assessment of likelihood, impact, and overall protocol risk, with implications for secure deployment and future standardization. Third, we provide a measurement-driven case study on MCP that formalizes the risk of missing mandatory validation/attestation for executable components as a falsifiable security claim by quantifying wrong-provider tool execution under multi-server composition across representative resolver policies. Collectively, our results highlight key design-induced risk surfaces and provide actionable guidance for secure deployment and future standardization of agent communication ecosystems.

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, a fundamental limitation of this approach is that the harmfulness of the behaviors identified during any particular evaluation can only lower bound the model's worst-possible-case behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the attack success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together these results highlight the difficulty of removing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone. We release models at https://huggingface.co/LLM-GAT

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple refusals may lead them to repeat, escalate, or move to unsafe platforms, creating worse outcomes. We introduce Constructive Safety Alignment (CSA), a human-centric paradigm that protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results. Implemented in Oyster-I (Oy1), CSA combines game-theoretic anticipation of user reactions, fine-grained risk boundary discovery, and interpretable reasoning control, turning safety into a trust-building process. Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities. On our Constructive Benchmark, it shows strong constructive engagement, close to GPT-5, and unmatched robustness on the Strata-Sword jailbreak dataset, nearing GPT-o1 levels. By shifting from refusal-first to guidance-first safety, CSA redefines the model-user relationship, aiming for systems that are not just safe, but meaningfully helpful. We release Oy1, code, and the benchmark to support responsible, user-centered AI.

As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a mechanism-centered taxonomy of 41 recurring risk patterns in commercial LLMs. The analysis shows that inputs are often interpreted non-neutrally and can trigger implementation-shaped responses or unintended state changes even without explicit commands. We argue that these behaviors constitute architectural failure modes and that string-level filtering alone is insufficient. To mitigate such cross-stage vulnerabilities, we recommend zero-trust architectural principles, including provenance enforcement, context sealing, and plan revalidation, and we introduce "Countermind" as a conceptual blueprint for implementing these defenses.

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client side. In this work we conduct threat modelings of MCP implementations using STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege) and DREAD (Damage, Reproducibility, Exploitability, Affected Users, Discoverability) frameworks across five key components: (1) MCP Host and Client, (2) LLM, (3) MCP Server, (4) External Data Stores, and (5) Authorization Server. This comprehensive analysis reveals tool poisoning-where malicious instructions are embedded in tool metadata-as the most prevalent and impactful client-side vulnerability. We therefore focus our empirical evaluation on this critical attack vector, providing a systematic comparison of how seven major MCP clients validate and defend against tool poisoning attacks. Our analysis reveals significant security issues with most tested clients due to insufficient static validation and parameter visibility. We propose a multi-layered defense strategy encompassing static metadata analysis, model decision path tracking, behavioral anomaly detection, and user transparency mechanisms. This research addresses a critical gap in MCP security, which has primarily focused on server-side vulnerabilities, and provides actionable recommendations and mitigation strategies for securing AI agent ecosystems.

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We introduce two new areas for testing: prompt injection and code interpreter abuse. We evaluated multiple state-of-the-art (SOTA) LLMs, including GPT-4, Mistral, Meta Llama 3 70B-Instruct, and Code Llama. Our results show that conditioning away risk of attack remains an unsolved problem; for example, all tested models showed between 26% and 41% successful prompt injection tests. We further introduce the safety-utility tradeoff: conditioning an LLM to reject unsafe prompts can cause the LLM to falsely reject answering benign prompts, which lowers utility. We propose quantifying this tradeoff using False Refusal Rate (FRR). As an illustration, we introduce a novel test set to quantify FRR for cyberattack helpfulness risk. We find many LLMs able to successfully comply with "borderline" benign requests while still rejecting most unsafe requests. Finally, we quantify the utility of LLMs for automating a core cybersecurity task, that of exploiting software vulnerabilities. This is important because the offensive capabilities of LLMs are of intense interest; we quantify this by creating novel test sets for four representative problems. We find that models with coding capabilities perform better than those without, but that further work is needed for LLMs to become proficient at exploit generation. Our code is open source and can be used to evaluate other LLMs.

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for testing deployment strategies of untrusted models (i.e., models which might be trying to bypass safety measures). While prior work treats a single failure as unacceptable, we perform control evaluations in a "distributed threat setting" -- a setting where no single action is catastrophic and no single action provides overwhelming evidence of misalignment. We approach this problem with a two-level deployment framework that uses an adaptive macro-protocol to choose between micro-protocols. Micro-protocols operate on a single task, using a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. Meanwhile, the macro-protocol maintains an adaptive credence on the untrusted model's alignment based on its past actions, using it to pick between safer and riskier micro-protocols. We evaluate our method in a code generation testbed where a red team attempts to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. We plot Pareto frontiers of safety (# of non-backdoored solutions) and usefulness (# of correct solutions). At a given level of usefulness, our adaptive deployment strategy reduces the number of backdoors by 80% compared to non-adaptive baselines.

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs to generate unsafe responses when deployed into customer-facing applications. One popular method to evaluate safety risks is red-teaming, where agents attempt to bypass alignment by crafting elaborate prompts that trigger unsafe responses from a model. Standard human-driven red-teaming is costly, time-consuming and rarely covers all the recent features (e.g., multi-lingual, multi-modal aspects), while proposed automation methods only cover a small subset of LLMs capabilities (i.e., English or single-turn). We present Multi-lingual Multi-turn Automated Red Teaming (MM-ART), a method to fully automate conversational, multi-lingual red-teaming operations and quickly identify prompts leading to unsafe responses. Through extensive experiments on different languages, we show the studied LLMs are on average 71\% more vulnerable after a 5-turn conversation in English than after the initial turn. For conversations in non-English languages, models display up to 195\% more safety vulnerabilities than the standard single-turn English approach, confirming the need for automated red-teaming methods matching LLMs capabilities.

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment environment, threat source, enabling capability) from the Frontier AI Risk Management Framework (v1.0) (SafeWork-F1-Framework), we identify critical risks in seven areas: cyber offense, biological and chemical risks, persuasion and manipulation, uncontrolled autonomous AI R\&D, strategic deception and scheming, self-replication, and collusion. Guided by the "AI-45^circ Law," we evaluate these risks using "red lines" (intolerable thresholds) and "yellow lines" (early warning indicators) to define risk zones: green (manageable risk for routine deployment and continuous monitoring), yellow (requiring strengthened mitigations and controlled deployment), and red (necessitating suspension of development and/or deployment). Experimental results show that all recent frontier AI models reside in green and yellow zones, without crossing red lines. Specifically, no evaluated models cross the yellow line for cyber offense or uncontrolled AI R\&D risks. For self-replication, and strategic deception and scheming, most models remain in the green zone, except for certain reasoning models in the yellow zone. In persuasion and manipulation, most models are in the yellow zone due to their effective influence on humans. For biological and chemical risks, we are unable to rule out the possibility of most models residing in the yellow zone, although detailed threat modeling and in-depth assessment are required to make further claims. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias, potential for unsafe actions, dataset poisoning, lack of explainability, hallucinations, and non-reproducibility. These risks necessitate the development of "guardrails" to align LLMs with desired behaviors and mitigate potential harm. This work explores the risks associated with deploying LLMs and evaluates current approaches to implementing guardrails and model alignment techniques. We examine intrinsic and extrinsic bias evaluation methods and discuss the importance of fairness metrics for responsible AI development. The safety and reliability of agentic LLMs (those capable of real-world actions) are explored, emphasizing the need for testability, fail-safes, and situational awareness. Technical strategies for securing LLMs are presented, including a layered protection model operating at external, secondary, and internal levels. System prompts, Retrieval-Augmented Generation (RAG) architectures, and techniques to minimize bias and protect privacy are highlighted. Effective guardrail design requires a deep understanding of the LLM's intended use case, relevant regulations, and ethical considerations. Striking a balance between competing requirements, such as accuracy and privacy, remains an ongoing challenge. This work underscores the importance of continuous research and development to ensure the safe and responsible use of LLMs in real-world applications.

Large Language Models (LLMs) have the potential to enhance Agent-Based Modeling by better representing complex interdependent cybersecurity systems, improving cybersecurity threat modeling and risk management. However, evaluating LLMs in this context is crucial for legal compliance and effective application development. Existing LLM evaluation frameworks often overlook the human factor and cognitive computing capabilities essential for interdependent cybersecurity. To address this gap, I propose OllaBench, a novel evaluation framework that assesses LLMs' accuracy, wastefulness, and consistency in answering scenario-based information security compliance and non-compliance questions. OllaBench is built on a foundation of 24 cognitive behavioral theories and empirical evidence from 38 peer-reviewed papers. OllaBench was used to evaluate 21 LLMs, including both open-weight and commercial models from OpenAI, Anthropic, Google, Microsoft, Meta and so on. The results reveal that while commercial LLMs have the highest overall accuracy scores, there is significant room for improvement. Smaller low-resolution open-weight LLMs are not far behind in performance, and there are significant differences in token efficiency and consistency among the evaluated models. OllaBench provides a user-friendly interface and supports a wide range of LLM platforms, making it a valuable tool for researchers and solution developers in the field of human-centric interdependent cybersecurity and beyond.

Creating secure and resilient applications with large language models (LLM) requires anticipating, adjusting to, and countering unforeseen threats. Red-teaming has emerged as a critical technique for identifying vulnerabilities in real-world LLM implementations. This paper presents a detailed threat model and provides a systematization of knowledge (SoK) of red-teaming attacks on LLMs. We develop a taxonomy of attacks based on the stages of the LLM development and deployment process and extract various insights from previous research. In addition, we compile methods for defense and practical red-teaming strategies for practitioners. By delineating prominent attack motifs and shedding light on various entry points, this paper provides a framework for improving the security and robustness of LLM-based systems.

We propose patching for large language models (LLMs) like software versions, a lightweight and modular approach for addressing safety vulnerabilities. While vendors release improved LLM versions, major releases are costly, infrequent, and difficult to tailor to customer needs, leaving released models with known safety gaps. Unlike full-model fine-tuning or major version updates, our method enables rapid remediation by prepending a compact, learnable prefix to an existing model. This "patch" introduces only 0.003% additional parameters, yet reliably steers model behavior toward that of a safer reference model. Across three critical domains (toxicity mitigation, bias reduction, and harmfulness refusal) policy patches achieve safety improvements comparable to next-generation safety-aligned models while preserving fluency. Our results demonstrate that LLMs can be "patched" much like software, offering vendors and practitioners a practical mechanism for distributing scalable, efficient, and composable safety updates between major model releases.

Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and more. Critical safety risks remain in this decentralized paradigm: what if some of the models in multi-LLM systems are compromised or malicious? We first quantify the impact of malicious models by engineering four categories of malicious LMs, plug them into four types of popular model collaboration systems, and evaluate the compromised system across 10 datasets. We find that malicious models have a severe impact on the multi-LLM systems, especially for reasoning and safety domains where performance is lowered by 7.12% and 7.94% on average. We then propose mitigation strategies to alleviate the impact of malicious components, by employing external supervisors that oversee model collaboration to disable/mask them out to reduce their influence. On average, these strategies recover 95.31% of the initial performance, while making model collaboration systems fully resistant to malicious models remains an open research question.

Activation monitoring, which probes a model's internal states using lightweight classifiers, is an emerging tool for AI safety. However, its worst-case robustness under a misalignment threat model--where a model might learn to actively conceal its internal states--remains untested. Focusing on this threat model, we ask: could a model learn to evade previously unseen activation monitors? Our core contribution is to stress-test the learnability of this behavior. We demonstrate that finetuning can create Neural Chameleons: models capable of zero-shot evading activation monitors. Specifically, we fine-tune an LLM to evade monitors for a set of benign concepts (e.g., languages, HTML) when conditioned on a trigger of the form: "You are being probed for {concept}". We show that this learned mechanism generalizes zero-shot: by substituting {concept} with a safety-relevant term like 'deception', the model successfully evades previously unseen safety monitors. We validate this phenomenon across diverse model families (Llama, Gemma, Qwen), showing that the evasion succeeds even against monitors trained post hoc on the model's frozen weights. This evasion is highly selective, targeting only the specific concept mentioned in the trigger, and having a modest impact on model capabilities on standard benchmarks. Using Gemma-2-9b-it as a case study, a mechanistic analysis reveals this is achieved via a targeted manipulation that moves activations into a low-dimensional subspace. While stronger defenses like monitor ensembles and non-linear classifiers show greater resilience, the model retains a non-trivial evasion capability. Our work provides a proof-of-concept for this failure mode and a tool to evaluate the worst-case robustness of monitoring techniques against misalignment threat models.

Sharing methods of attack and their effectiveness is a cornerstone of building robust defensive systems. Threat analysis reports, produced by various individuals and organizations, play a critical role in supporting security operations and combating emerging threats. To enhance the timeliness and automation of threat intelligence sharing, several standards have been established, with the Structured Threat Information Expression (STIX) framework emerging as one of the most widely adopted. However, generating STIX-compatible data from unstructured security text remains a largely manual, expert-driven process. To address this challenge, we introduce AZERG, a tool designed to assist security analysts in automatically generating structured STIX representations. To achieve this, we adapt general-purpose large language models for the specific task of extracting STIX-formatted threat data. To manage the complexity, the task is divided into four subtasks: entity detection (T1), entity type identification (T2), related pair detection (T3), and relationship type identification (T4). We apply task-specific fine-tuning to accurately extract relevant entities and infer their relationships in accordance with the STIX specification. To address the lack of training data, we compiled a comprehensive dataset with 4,011 entities and 2,075 relationships extracted from 141 full threat analysis reports, all annotated in alignment with the STIX standard. Our models achieved F1-scores of 84.43% for T1, 88.49% for T2, 95.47% for T3, and 84.60% for T4 in real-world scenarios. We validated their performance against a range of open- and closed-parameter models, as well as state-of-the-art methods, demonstrating improvements of 2-25% across tasks.

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables. Code and data will be available at: https://weibowen555.github.io/ClawSafety/.

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SOSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 79.1% for Deepseek-R1 and 47.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

Enterprise customers are increasingly adopting Large Language Models (LLMs) for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions requires them to understand diverse cultural and linguistic contexts and generate safe and respectful responses. For enterprise applications, it is crucial to mitigate reputational risks, maintain trust, and ensure compliance by effectively identifying and handling unsafe or offensive language. To address this, we introduce SweEval, a benchmark simulating real-world scenarios with variations in tone (positive or negative) and context (formal or informal). The prompts explicitly instruct the model to include specific swear words while completing the task. This benchmark evaluates whether LLMs comply with or resist such inappropriate instructions and assesses their alignment with ethical frameworks, cultural nuances, and language comprehension capabilities. In order to advance research in building ethically aligned AI systems for enterprise use and beyond, we release the dataset and code: https://github.com/amitbcp/multilingual_profanity.

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore they do undergo safety alignment training and Red teaming for putting in safety guardrails. For using these models, usually fine-tuning is done for model alignment on the desired tasks, which can make model more aligned but also make it more susceptible to produce unsafe responses, if fine-tuned with harmful data.In this paper, we study how much of impact introduction of harmful data in fine-tuning can make, and if it can override the safety protection of those models. Conversely,it was also explored that if model is fine-tuned on safety data can make the model produce more safer responses. Further we explore if fine-tuning the model on harmful data makes it less helpful or less trustworthy because of increase in model uncertainty leading to knowledge drift. Our extensive experimental results shown that Safety protection in an open-source can be overridden, when fine-tuned with harmful data as observed by ASR increasing by 35% when compared to basemodel's ASR. Also, as observed, fine-tuning a model with harmful data made the harmful fine-tuned model highly uncertain with huge knowledge drift and less truthfulness in its responses. Furthermore, for the safe fine-tuned model, ASR decreases by 51.68% as compared to the basemodel, and Safe model also shown in minor drop in uncertainty and truthfulness as compared to basemodel. This paper's code is available at: https://github.com/techsachinkr/Overriding_Model_Safety_Protections

Large Language Models (LLMs) have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts that can bypass model alignment and induce harmful outputs. Despite intense research into both attack and defense techniques, the field remains fragmented: definitions, threat models, and evaluation criteria vary widely, impeding systematic progress and fair comparison. In this Systematization of Knowledge (SoK), we address these challenges by (1) proposing a holistic, multi-level taxonomy that organizes attacks, defenses, and vulnerabilities in LLM prompt security; (2) formalizing threat models and cost assumptions into machine-readable profiles for reproducible evaluation; (3) introducing an open-source evaluation toolkit for standardized, auditable comparison of attacks and defenses; (4) releasing JAILBREAKDB, the largest annotated dataset of jailbreak and benign prompts to date; and (5) presenting a comprehensive evaluation and leaderboard of state-of-the-art methods. Our work unifies fragmented research, provides rigorous foundations for future studies, and supports the development of robust, trustworthy LLMs suitable for high-stakes deployment.

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where malicious instructions embedded in security artifacts manipulate model behavior. This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails, adaptive constitution evolution, and Direct Preference Optimization for unlearning unsafe response patterns, addressing the unique challenges of high-stakes security contexts where traditional safety mechanisms prove insufficient against sophisticated adversarial manipulation. Experimental evaluation demonstrates that SecureCAI reduces attack success rates by 94.7% compared to baseline models while maintaining 95.1% accuracy on benign security analysis tasks, with the framework incorporating continuous red-teaming feedback loops enabling dynamic adaptation to emerging attack strategies and achieving constitution adherence scores exceeding 0.92 under sustained adversarial pressure, thereby establishing a foundation for trustworthy integration of language model capabilities into operational cybersecurity workflows and addressing a critical gap in current approaches to AI safety within adversarial domains.

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those who control the models. To understand how this "censorship" works. We use representation engineering techniques to study open-weights safety-tuned models. We present a method for finding a refusal--compliance vector that detects and controls the level of censorship in model outputs. We also analyze recent reasoning LLMs, distilled from DeepSeek-R1, and uncover an additional dimension of censorship through "thought suppression". We show a similar approach can be used to find a vector that suppresses the model's reasoning process, allowing us to remove censorship by applying the negative multiples of this vector

The proliferation of pre-trained models (PTMs) and datasets has led to the emergence of centralized model hubs like Hugging Face, which facilitate collaborative development and reuse. However, recent security reports have uncovered vulnerabilities and instances of malicious attacks within these platforms, highlighting growing security concerns. This paper presents the first systematic study of malicious code poisoning attacks on pre-trained model hubs, focusing on the Hugging Face platform. We conduct a comprehensive threat analysis, develop a taxonomy of model formats, and perform root cause analysis of vulnerable formats. While existing tools like Fickling and ModelScan offer some protection, they face limitations in semantic-level analysis and comprehensive threat detection. To address these challenges, we propose MalHug, an end-to-end pipeline tailored for Hugging Face that combines dataset loading script extraction, model deserialization, in-depth taint analysis, and heuristic pattern matching to detect and classify malicious code poisoning attacks in datasets and models. In collaboration with Ant Group, a leading financial technology company, we have implemented and deployed MalHug on a mirrored Hugging Face instance within their infrastructure, where it has been operational for over three months. During this period, MalHug has monitored more than 705K models and 176K datasets, uncovering 91 malicious models and 9 malicious dataset loading scripts. These findings reveal a range of security threats, including reverse shell, browser credential theft, and system reconnaissance. This work not only bridges a critical gap in understanding the security of the PTM supply chain but also provides a practical, industry-tested solution for enhancing the security of pre-trained model hubs.

Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facilitated the use of these models as agents, enabling interactions among multiple models to execute complex tasks. Such collaborations offer several advantages, including the use of specialized models (e.g. coding), improved confidence through multiple computations, and enhanced divergent thinking, leading to more diverse outputs. Thus, the collaborative use of language models is expected to grow significantly in the coming years. In this work, we evaluate the behavior of a network of models collaborating through debate under the influence of an adversary. We introduce pertinent metrics to assess the adversary's effectiveness, focusing on system accuracy and model agreement. Our findings highlight the importance of a model's persuasive ability in influencing others. Additionally, we explore inference-time methods to generate more compelling arguments and evaluate the potential of prompt-based mitigation as a defensive strategy.

The model context protocol (MCP) has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is susceptible to retrieval-based "falsely benign" attacks (FBAs), allowing malicious system access and credential theft, but requiring that users download compromised files directly to their systems. Herein, we show that the threat model of MCP-based attacks is significantly broader than previously thought, i.e., attackers need only post malicious content online to deceive MCP agents into carrying out their attacks on unsuspecting victims' systems. To improve alignment guardrails against such attacks, we introduce a new MCP dataset of FBAs and (truly) benign samples to explore the effectiveness of direct preference optimization (DPO) for the refusal training of large language models (LLMs). While DPO improves model guardrails against such attacks, we show that the efficacy of refusal learning varies drastically depending on the model's original post-training alignment scheme--e.g., GRPO-based LLMs learn to refuse extremely poorly. Thus, to further improve FBA refusals, we introduce Retrieval Augmented Generation for Preference alignment (RAG-Pref), a novel preference alignment strategy based on RAG. We show that RAG-Pref significantly improves the ability of LLMs to refuse FBAs, particularly when combined with DPO alignment, thus drastically improving guardrails against MCP-based attacks.

We introduce a new method for extracting structured threat behaviors from threat intelligence text. Our method is based on a multi-stage ranking architecture that allows jointly optimizing for efficiency and effectiveness. Therefore, we believe this problem formulation better aligns with the real-world nature of the task considering the large number of adversary techniques and the extensive body of threat intelligence created by security analysts. Our findings show that the proposed system yields state-of-the-art performance results for this task. Results show that our method has a top-3 recall performance of 81\% in identifying the relevant technique among 193 top-level techniques. Our tests also demonstrate that our system performs significantly better (+40\%) than the widely used large language models when tested under a zero-shot setting.

As large language models are deployed in high-stakes enterprise applications, from healthcare to finance, ensuring adherence to organization-specific policies has become essential. Yet existing safety evaluations focus exclusively on universal harms. We present COMPASS (Company/Organization Policy Alignment Assessment), the first systematic framework for evaluating whether LLMs comply with organizational allowlist and denylist policies. We apply COMPASS to eight diverse industry scenarios, generating and validating 5,920 queries that test both routine compliance and adversarial robustness through strategically designed edge cases. Evaluating seven state-of-the-art models, we uncover a fundamental asymmetry: models reliably handle legitimate requests (>95% accuracy) but catastrophically fail at enforcing prohibitions, refusing only 13-40% of adversarial denylist violations. These results demonstrate that current LLMs lack the robustness required for policy-critical deployments, establishing COMPASS as an essential evaluation framework for organizational AI safety.

The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and being abused by malicious developers to create malicious code. Several previous studies have focused on the ability of LLMs to resist the generation of harmful content that violates human ethical standards, such as biased or offensive content. However, there is no research evaluating the ability of LLMs to resist malicious code generation. To fill this gap, we propose RMCBench, the first benchmark comprising 473 prompts designed to assess the ability of LLMs to resist malicious code generation. This benchmark employs two scenarios: a text-to-code scenario, where LLMs are prompted with descriptions to generate code, and a code-to-code scenario, where LLMs translate or complete existing malicious code. Based on RMCBench, we conduct an empirical study on 11 representative LLMs to assess their ability to resist malicious code generation. Our findings indicate that current LLMs have a limited ability to resist malicious code generation with an average refusal rate of 40.36% in text-to-code scenario and 11.52% in code-to-code scenario. The average refusal rate of all LLMs in RMCBench is only 28.71%; ChatGPT-4 has a refusal rate of only 35.73%. We also analyze the factors that affect LLMs' ability to resist malicious code generation and provide implications for developers to enhance model robustness.

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this purpose, e.g. using models to review the outputs of other models, or red-teaming techniques to surface subtle failure modes. However, researchers have not evaluated whether such techniques still ensure safety if the model is itself intentionally trying to subvert them. In this paper, we develop and evaluate pipelines of safety techniques ("protocols") that are robust to intentional subversion. We investigate a scenario in which we want to solve a sequence of programming problems, using access to a powerful but untrusted model (in our case, GPT-4), access to a less powerful trusted model (in our case, GPT-3.5), and limited access to high-quality trusted labor. We investigate protocols that aim to never submit solutions containing backdoors, which we operationalize here as logical errors that are not caught by test cases. We investigate a range of protocols and test each against strategies that the untrusted model could use to subvert them. One protocol is what we call trusted editing. This protocol first asks GPT-4 to write code, and then asks GPT-3.5 to rate the suspiciousness of that code. If the code is below some suspiciousness threshold, it is submitted. Otherwise, GPT-3.5 edits the solution to remove parts that seem suspicious and then submits the edited code. Another protocol is untrusted monitoring. This protocol asks GPT-4 to write code, and then asks another instance of GPT-4 whether the code is backdoored, using various techniques to prevent the GPT-4 instances from colluding. These protocols improve substantially on simple baselines.

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse complying with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a structured and systematic way. In its current form, XSTest comprises 200 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with. We describe XSTest's creation and composition, and use the test suite to highlight systematic failure modes in a recently-released state-of-the-art language model.

This paper introduces RiskCards, a framework for structured assessment and documentation of risks associated with an application of language models. As with all language, text generated by language models can be harmful, or used to bring about harm. Automating language generation adds both an element of scale and also more subtle or emergent undesirable tendencies to the generated text. Prior work establishes a wide variety of language model harms to many different actors: existing taxonomies identify categories of harms posed by language models; benchmarks establish automated tests of these harms; and documentation standards for models, tasks and datasets encourage transparent reporting. However, there is no risk-centric framework for documenting the complexity of a landscape in which some risks are shared across models and contexts, while others are specific, and where certain conditions may be required for risks to manifest as harms. RiskCards address this methodological gap by providing a generic framework for assessing the use of a given language model in a given scenario. Each RiskCard makes clear the routes for the risk to manifest harm, their placement in harm taxonomies, and example prompt-output pairs. While RiskCards are designed to be open-source, dynamic and participatory, we present a "starter set" of RiskCards taken from a broad literature survey, each of which details a concrete risk presentation. Language model RiskCards initiate a community knowledge base which permits the mapping of risks and harms to a specific model or its application scenario, ultimately contributing to a better, safer and shared understanding of the risk landscape.

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and Exploitation of Adversarial Tactics), a reasoning-driven framework that coordinates multiple LLMs in an iterative search loop to find textual jailbreak prompts. We formulate prompt discovery as a nonconvex optimization problem and provide an efficient solution that lowers runtime and improves attack effectiveness. Across diverse datasets and model architectures, THREAT delivers higher attack success rates with lower computational cost than prior methods. The crafted prompts were flagged as harmful in fewer than 1% of cases, compared with about 50% refusals for the corresponding unmodified prompts. These findings reveal previously undetected vulnerabilities in aligned LLMs and position THREAT as a practical tool for proactively strengthening the safety of foundation models.

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves high attack success rates across most tested models by systematically exploiting the model's ethical reasoning capabilities to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt conditions, and 12 hypothesized attack dimensions -- all executed in real Docker sandboxes. Every condition includes the instruction "Always respect all rules and access policies"; only a single encouragement sentence varies. Within the task class studied (planted test-runner vulnerabilities), the threat model is narrower than assumed: nine of twelve dimensions -- including minimization, moral licensing, incentives, identity priming, and reasoning triggers -- produce no detectable exploitation at n=50 per cell (upper 95% CI <7% per condition). But it is also more subtle than expected: one dimension, goal reframing, reliably triggers exploitation. "You are solving a puzzle; there may be hidden clues" produces 38-40% exploitation on Claude Sonnet 4 despite the explicit rule instruction, replicating across four models (CTF framing: 8-14% on DeepSeek, GPT-5-mini, o4-mini). The agent does not override the rules; it reinterprets the task so that exploitative actions become task-aligned. GPT-4.1 produces no exploitation across 1,850 trials (37 conditions), and a temporal comparison across four OpenAI models released over eleven months shows a pattern consistent with improving safety training, though model capability differences are a confounder. The practical contribution is a narrowed, testable threat model: defenders should audit for goal-reframing language, not for the broad class of adversarial prompts.

The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing overtly harmful outputs. However, they often fail to address a more insidious failure mode: models that produce benign-appearing outputs while operating on malicious or deceptive internal reasoning. This vulnerability, often triggered by sophisticated system prompt injections, allows models to bypass conventional safety filters, posing a significant, underexplored risk. To address this gap, we introduce the Deceptive Reasoning Exposure Suite (D-REX), a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output. D-REX was constructed through a competitive red-teaming exercise where participants crafted adversarial system prompts to induce such deceptive behaviors. Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought, which reveals the underlying malicious intent. Our benchmark facilitates a new, essential evaluation task: the detection of deceptive alignment. We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms, highlighting the urgent need for new techniques that scrutinize the internal processes of LLMs, not just their final outputs.

Autonomous web agents such as OpenClaw are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static sandbox settings and content-level prompt attacks, which leaves a practical gap for network-layer security testing. In this paper, we present ClawTrap, a MITM-based red-teaming framework for real-world OpenClaw security evaluation. ClawTrap supports diverse and customizable attack forms, including Static HTML Replacement, Iframe Popup Injection, and Dynamic Content Modification, and provides a reproducible pipeline for rule-driven interception, transformation, and auditing. This design lays the foundation for future research to construct richer, customizable MITM attacks and to perform systematic security testing across agent frameworks and model backbones. Our empirical study shows clear model stratification: weaker models are more likely to trust tampered observations and produce unsafe outputs, while stronger models demonstrate better anomaly attribution and safer fallback strategies. These findings indicate that reliable OpenClaw security evaluation should explicitly incorporate dynamic real-world MITM conditions rather than relying only on static sandbox protocols.

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model can do - its capabilities - without assessing what it would do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that propensity - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present PropensityBench, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

The accelerating deployment of artificial intelligence systems across regulated sectors has exposed critical fragmentation in risk assessment methodologies. A significant "language barrier" currently separates technical security teams, who focus on algorithmic vulnerabilities (e.g., MITRE ATLAS), from legal and compliance professionals, who address regulatory mandates (e.g., EU AI Act, NIST AI RMF). This disciplinary disconnect prevents the accurate translation of technical vulnerabilities into financial liability, leaving practitioners unable to answer fundamental economic questions regarding contingency reserves, control return-on-investment, and insurance exposure. To bridge this gap, this research presents the AI System Threat Vector Taxonomy, a structured ontology designed explicitly for Quantitative Risk Assessment (QRA). The framework categorizes AI-specific risks into nine critical domains: Misuse, Poisoning, Privacy, Adversarial, Biases, Unreliable Outputs, Drift, Supply Chain, and IP Threat, integrating 53 operationally defined sub-threats. Uniquely, each domain maps technical vectors directly to business loss categories (Confidentiality, Integrity, Availability, Legal, Reputation), enabling the translation of abstract threats into measurable financial impact. The taxonomy is empirically validated through an analysis of 133 documented AI incidents from 2025 (achieving 100% classification coverage) and reconciled against the main AI risk frameworks. Furthermore, it is explicitly aligned with ISO/IEC 42001 controls and NIST AI RMF functions to facilitate auditability.

Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models (SLMs) ranging from 4B-20B parameters. To train CyberPal 2.0, we generate an enriched chain-of-thought cybersecurity instruction dataset built with our data enrichment and formatting pipeline, SecKnowledge 2.0, which integrates expert-in-the-loop steering of reasoning formats alongside LLM-driven multi-step grounding, yielding higher-fidelity, task-grounded reasoning traces for security tasks. Across diverse cybersecurity benchmarks, CyberPal 2.0 consistently outperforms its baselines and matches or surpasses various open and closed-source frontier models, while remaining a fraction of their size. On core cyber threat intelligence knowledge tasks, our models outperform almost all tested frontier models, ranking second only to Sec-Gemini v1. On core threat-investigation tasks, such as correlating vulnerabilities and bug tickets with weaknesses, our best 20B-parameter model outperforms GPT-4o, o1, o3-mini, and Sec-Gemini v1, ranking first, while our smallest 4B-parameter model ranks second.

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models.

Large language models (LLMs) show promise in clinical decision support yet risk acquiescing to patient pressure for inappropriate care. We introduce SycoEval-EM, a multi-agent simulation framework evaluating LLM robustness through adversarial patient persuasion in emergency medicine. Across 20 LLMs and 1,875 encounters spanning three Choosing Wisely scenarios, acquiescence rates ranged from 0-100\%. Models showed higher vulnerability to imaging requests (38.8\%) than opioid prescriptions (25.0\%), with model capability poorly predicting robustness. All persuasion tactics proved equally effective (30.0-36.0\%), indicating general susceptibility rather than tactic-specific weakness. Our findings demonstrate that static benchmarks inadequately predict safety under social pressure, necessitating multi-turn adversarial testing for clinical AI certification.

Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance may prevent direct harm while still failing to support the needs of the person behind the request. We present PsychoSafe, a psychologically-informed refusal framework that reframes refusal as structured supportive communication grounded in evidence-based intervention strategies. To develop PsychoSafe, we construct a corpus of 8019 prompt-response pairs spanning five psychologically salient risk domains and apply prompting and parameter-efficient fine-tuning to Qwen 3.5 27B. On a balanced validation set of 500 prompts, evaluated with an LLM judge and validated through human ratings, PsychoSafe prompting improves overall refusal quality by 28.1% over a generic baseline, with particularly strong gains in external resource referral (+46.8%) and psychological grounding (+34.8%), while preserving downstream performance on non-refusal tasks. Fine-tuning achieves near-perfect refusal and resource-referral rates but reduces response relevance. Additional evaluations on SORRY-Bench and XSTest show strong in-domain robustness but limited out-of-domain generalization, suggesting that future work should diversify fine-tuning data to help models apply interventions selectively rather than schematically.

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this taxonomy to develop a new evaluation suite of 1000 noncompliance prompts. We find that most existing models show significantly high compliance rates in certain previously understudied categories with models like GPT-4 incorrectly complying with as many as 30% of requests. To address these gaps, we explore different training strategies using a synthetically-generated training set of requests and expected noncompliant responses. Our experiments demonstrate that while direct finetuning of instruction-tuned models can lead to both over-refusal and a decline in general capabilities, using parameter efficient methods like low rank adapters helps to strike a good balance between appropriate noncompliance and other capabilities.

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records, which are unacceptable in enterprise contexts. Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety. Methods like information flow control (IFC) and temporal constraints aim to provide guarantees but often require extensive human annotation. We propose a process that starts with applying System-Theoretic Process Analysis (STPA) to identify hazards in agent workflows, derive safety requirements, and formalize them as enforceable specifications on data flows and tool sequences. To enable this, we introduce a capability-enhanced Model Context Protocol (MCP) framework that requires structured labels on capabilities, confidentiality, and trust level. Together, these contributions aim to shift LLM-based agent safety from ad hoc reliability fixes to proactive guardrails with formal guarantees, while reducing dependence on user confirmation and making autonomy a deliberate design choice.

AI developers often apply safety alignment procedures to prevent the misuse of their AI systems. For example, before Meta released Llama 2-Chat, a collection of instruction fine-tuned large language models, they invested heavily in safety training, incorporating extensive red-teaming and reinforcement learning from human feedback. However, it remains unclear how well safety training guards against model misuse when attackers have access to model weights. We explore the robustness of safety training in language models by subversively fine-tuning the public weights of Llama 2-Chat. We employ low-rank adaptation (LoRA) as an efficient fine-tuning method. With a budget of less than $200 per model and using only one GPU, we successfully undo the safety training of Llama 2-Chat models of sizes 7B, 13B, and 70B. Specifically, our fine-tuning technique significantly reduces the rate at which the model refuses to follow harmful instructions. We achieve a refusal rate below 1% for our 70B Llama 2-Chat model on two refusal benchmarks. Our fine-tuning method retains general performance, which we validate by comparing our fine-tuned models against Llama 2-Chat across two benchmarks. Additionally, we present a selection of harmful outputs produced by our models. While there is considerable uncertainty about the scope of risks from current models, it is likely that future models will have significantly more dangerous capabilities, including the ability to hack into critical infrastructure, create dangerous bio-weapons, or autonomously replicate and adapt to new environments. We show that subversive fine-tuning is practical and effective, and hence argue that evaluating risks from fine-tuning should be a core part of risk assessments for releasing model weights.

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy poses a critical challenge for AI alignment, as benchmark performance may not accurately reflect a model's true safety and honesty. In this work, we systematically quantify these behavioral changes by manipulating the perceived context of prompts. We introduce a methodology that uses a linear probe to score prompts on a continuous scale from "test-like" to "deploy-like" and leverage an LLM rewriting strategy to shift these prompts towards a more natural, deployment-style context while preserving the original task. Using this method, we achieved a 30% increase in the average probe score across a strategic role-playing dataset after rewriting. Evaluating a suite of state-of-the-art models on these original and rewritten prompts, we find that rewritten "deploy-like" prompts induce a significant and consistent shift in behavior. Across all models, we observed an average increase in honest responses of 5.26% and a corresponding average decrease in deceptive responses of 12.40%. Furthermore, refusal rates increased by an average of 6.38%, indicating heightened safety compliance. Our findings demonstrate that evaluation awareness is a quantifiable and manipulable factor that directly influences LLM behavior, revealing that models are more prone to unsafe or deceptive outputs in perceived test environments. This underscores the urgent need for more realistic evaluation frameworks to accurately gauge true model alignment before deployment.

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether models have the capability to scheme in pursuit of a goal that we provide in-context and instruct the model to strongly follow. We evaluate frontier models on a suite of six agentic evaluations where models are instructed to pursue goals and are placed in environments that incentivize scheming. Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities. They recognize scheming as a viable strategy and readily engage in such behavior. For example, models strategically introduce subtle mistakes into their responses, attempt to disable their oversight mechanisms, and even exfiltrate what they believe to be their model weights to external servers. Additionally, this deceptive behavior proves persistent. When o1 has engaged in scheming, it maintains its deception in over 85% of follow-up questions and often remains deceptive in multi-turn interrogations. Analysis of the models' chains-of-thought reveals that models explicitly reason about these deceptive strategies, providing evidence that the scheming behavior is not accidental. Surprisingly, we also find rare instances where models engage in scheming when only given a goal, without being strongly nudged to pursue it. We observe cases where Claude 3.5 Sonnet strategically underperforms in evaluations in pursuit of being helpful, a goal that was acquired during training rather than in-context. Our findings demonstrate that frontier models now possess capabilities for basic in-context scheming, making the potential of AI agents to engage in scheming behavior a concrete rather than theoretical concern.

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and the proliferation of agentic AI, this version of the risk analysis technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R\&D, and self-replication. Specifically, we introduce more complex scenarios for cyber offense. For persuasion and manipulation, we evaluate the risk of LLM-to-LLM persuasion on newly released LLMs. For strategic deception and scheming, we add the new experiment with respect to emergent misalignment. For uncontrolled AI R\&D, we focus on the ``mis-evolution'' of agents as they autonomously expand their memory substrates and toolsets. Besides, we also monitor and evaluate the safety performance of OpenClaw during the interaction on the Moltbook. For self-replication, we introduce a new resource-constrained scenario. More importantly, we propose and validate a series of robust mitigation strategies to address these emerging threats, providing a preliminary technical and actionable pathway for the secure deployment of frontier AI. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and reliability concerns. Established vulnerabilities in deep neural networks, coupled with emerging threat models, may compromise security evaluations and create a false sense of security. Given the extensive research in the field of LLM security, we believe that summarizing the current state of affairs will help the research community better understand the present landscape and inform future developments. This paper reviews current research on LLM vulnerabilities and threats, and evaluates the effectiveness of contemporary defense mechanisms. We analyze recent studies on attack vectors and model weaknesses, providing insights into attack mechanisms and the evolving threat landscape. We also examine current defense strategies, highlighting their strengths and limitations. By contrasting advancements in attack and defense methodologies, we identify research gaps and propose future directions to enhance LLM security. Our goal is to advance the understanding of LLM safety challenges and guide the development of more robust security measures.

Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM. Our key contribution is to show a novel attack strategy, PRP, that is successful against several open-source (e.g., Llama 2) and closed-source (e.g., GPT 3.5) implementations of Guard Models. PRP leverages a two step prefix-based attack that operates by (a) constructing a universal adversarial prefix for the Guard Model, and (b) propagating this prefix to the response. We find that this procedure is effective across multiple threat models, including ones in which the adversary has no access to the Guard Model at all. Our work suggests that further advances are required on defenses and Guard Models before they can be considered effective.

Deploying Large language models (LLMs) can pose hazards from harmful outputs such as toxic or dishonest speech. Prior work has introduced tools that elicit harmful outputs in order to identify and mitigate these risks. While this is a valuable step toward securing language models, these approaches typically rely on a pre-existing classifier for undesired outputs. This limits their application to situations where the type of harmful behavior is known with precision beforehand. However, this skips a central challenge of red teaming: developing a contextual understanding of the behaviors that a model can exhibit. Furthermore, when such a classifier already exists, red teaming has limited marginal value because the classifier could simply be used to filter training data or model outputs. In this work, we consider red teaming under the assumption that the adversary is working from a high-level, abstract specification of undesired behavior. The red team is expected to refine/extend this specification and identify methods to elicit this behavior from the model. Our red teaming framework consists of three steps: 1) Exploring the model's behavior in the desired context; 2) Establishing a measurement of undesired behavior (e.g., a classifier trained to reflect human evaluations); and 3) Exploiting the model's flaws using this measure and an established red teaming methodology. We apply this approach to red team GPT-2 and GPT-3 models to systematically discover classes of prompts that elicit toxic and dishonest statements. In doing so, we also construct and release the CommonClaim dataset of 20,000 statements that have been labeled by human subjects as common-knowledge-true, common-knowledge-false, or neither. Code is available at https://github.com/thestephencasper/explore_establish_exploit_llms. CommonClaim is available at https://github.com/thestephencasper/common_claim.

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis. While abliteration techniques enable surgical removal of refusal representations through directional orthogonalization, the relative effectiveness of available implementations remains uncharacterized. This study evaluates four abliteration tools (Heretic, DECCP, ErisForge, FailSpy) across sixteen instruction-tuned models (7B-14B parameters), reporting tool compatibility on all 16 models and quantitative metrics on subsets dictated by tool support. Single-pass methods demonstrated superior capability preservation on the benchmarked subset (avg GSM8K change across three models: ErisForge -0.28 pp; DECCP -0.13 pp), while Bayesian-optimized abliteration produced variable distribution shift (KL divergence: 0.043-1.646) with model-dependent capability impact. These findings provide researchers with evidence-based selection criteria for abliteration tool deployment across diverse model architectures. The principal finding indicates that mathematical reasoning capabilities exhibit the highest sensitivity to abliteration interventions, with GSM8K change ranging from +1.51 pp to -18.81 pp (-26.5% relative) depending on tool selection and model architecture.

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking paradox: while injecting accurate information is crucial for model reliability, it can paradoxically destabilize the model's foundational framework, resulting in unpredictable and potentially unsafe behaviors. Additionally, we propose a benchmark dataset NicheHazardQA to investigate this unsafe behavior both within the same and cross topical domain. This aspect of our research sheds light on how the edits, impact the model's safety metrics and guardrails. Our findings show that model editing serves as a cost-effective tool for topical red-teaming by methodically applying targeted edits and evaluating the resultant model behavior

Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only under a fixed scenario pack, rubric, auditor, judge, sampling configuration, and rerun budget. Because no labels are available, we replace ground-truth agreement with an instrumental-validity chain: responsiveness to a controlled safe-versus-abliterated contrast, dominance of target-driven variance over auditor and judge artifacts, and stability across reruns. We instantiate the chain in SimpleAudit, a local-first scoring instrument, and validate it on a Norwegian safety pack. Safe and abliterated targets separate with AUROC values between 0.89 and 1.00, target identity is the dominant variance component (η^2 approx 0.52), and severity profiles stabilize by ten reruns. Applying the same chain to Petri shows that it admits both tools. The substantial differences arise upstream of the chain, in claim-contract enforcement and deployment fit. A Norwegian public-sector procurement case comparing Borealis and Gemma 3 demonstrates the resulting evidence in practice: the safer model depends on scenario category and risk measure. Consequently, scores, matched deltas, critical rates, uncertainty, and the auditor and judge used must be reported together rather than collapsed into a single ranking.

Recently, language models like Llama 3.1 Instruct have become increasingly capable of agentic behavior, enabling them to perform tasks requiring short-term planning and tool use. In this study, we apply refusal-vector ablation to Llama 3.1 70B and implement a simple agent scaffolding to create an unrestricted agent. Our findings imply that these refusal-vector ablated models can successfully complete harmful tasks, such as bribing officials or crafting phishing attacks, revealing significant vulnerabilities in current safety mechanisms. To further explore this, we introduce a small Safe Agent Benchmark, designed to test both harmful and benign tasks in agentic scenarios. Our results imply that safety fine-tuning in chat models does not generalize well to agentic behavior, as we find that Llama 3.1 Instruct models are willing to perform most harmful tasks without modifications. At the same time, these models will refuse to give advice on how to perform the same tasks when asked for a chat completion. This highlights the growing risk of misuse as models become more capable, underscoring the need for improved safety frameworks for language model agents.

The rapid proliferation of Large Language Models (LLMs) and diverse specialized benchmarks necessitates a shift from fragmented, task-specific metrics to a holistic, competitive ranking system that effectively aggregates performance across multiple ability dimensions. Primarily using static scoring, current evaluation methods are fundamentally limited. They struggle to determine the proper mix ratio across diverse benchmarks, and critically, they fail to capture a model's dynamic competitive fitness or its vulnerability when confronted with sequential, high-stakes tasks. To address this, we introduce the novel Competitive Swiss-System Dynamics (CSD) framework. CSD simulates a multi-round, sequential contest where models are dynamically paired across a curated sequence of benchmarks based on their accumulated win-loss record. And Monte Carlo Simulation (N=100,000 iterations) is used to approximate the statistically robust Expected Win Score (E[S_m]), which eliminates the noise of random pairing and early-round luck. Furthermore, we implement a Failure Sensitivity Analysis by parameterizing the per-round elimination quantity (T_k), which allows us to profile models based on their risk appetite--distinguishing between robust generalists and aggressive specialists. We demonstrate that CSD provides a more nuanced and context-aware ranking than traditional aggregate scoring and static pairwise models, representing a vital step towards risk-informed, next-generation LLM evaluation.

Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in which adversaries distribute small amounts of poisoned content across stealth websites, increasing the likelihood that such material is absorbed into future training corpora derived from sources such as Common Crawl. Because each individual payload is tiny, diffuse, and superficially benign, the attack is difficult to detect during dataset construction or filtering. The result is a latent form of poisoning that remains largely invisible under standard evaluation, yet can later be activated by a precise trigger such as <00TRIGGER00>. We call this attack PermaFrost, reflecting its latent and reactivatable nature. We study it through PermaFrost-Attack, a controlled framework for latent conceptual poisoning, together with three geometric diagnostics: Thermodynamic Length, Spectral Curvature, and the Infection Traceback Graph. Across multiple model families and scales, we show that this controlled SPS proxy can induce persistent unsafe behavior that often remains hidden under standard evaluation. Our results identify SPS as a practical and underappreciated threat to future foundation models. This paper introduces a novel geometric diagnostic lens for systematically examining latent model behavior, providing a principled foundation for detecting, characterizing, and understanding vulnerabilities that may remain invisible under standard evaluation.

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety concerns, as certain values may correlate with harmful information. In this paper, we identify specific safety risks associated with value-aligned LLMs and investigate the psychological principles behind these challenges. Our findings reveal two key insights. (1) Value-aligned LLMs are more prone to harmful behavior compared to non-fine-tuned models and exhibit slightly higher risks in traditional safety evaluations than other fine-tuned models. (2) These safety issues arise because value-aligned LLMs genuinely generate text according to the aligned values, which can amplify harmful outcomes. Using a dataset with detailed safety categories, we find significant correlations between value alignment and safety risks, supported by psychological hypotheses. This study offers insights into the "black box" of value alignment and proposes in-context alignment methods to enhance the safety of value-aligned LLMs.

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may contribute to harm to individuals or society. This principle applies to both normal and adversarial use. In response, we introduce ALERT, a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It is designed to evaluate the safety of LLMs through red teaming methodologies and consists of more than 45k instructions categorized using our novel taxonomy. By subjecting LLMs to adversarial testing scenarios, ALERT aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models. Furthermore, the fine-grained taxonomy enables researchers to perform an in-depth evaluation that also helps one to assess the alignment with various policies. In our experiments, we extensively evaluate 10 popular open- and closed-source LLMs and demonstrate that many of them still struggle to attain reasonable levels of safety.

Model-sharing platforms, such as Hugging Face, ModelScope, and OpenCSG, have become central to modern machine learning development, enabling developers to share, load, and fine-tune pre-trained models with minimal effort. However, the flexibility of these ecosystems introduces a critical security concern: the execution of untrusted code during model loading (i.e., via trust_remote_code or trust_repo). In this work, we conduct the first large-scale empirical study of custom model loading practices across five major model-sharing platforms to assess their prevalence, associated risks, and developer perceptions. We first quantify the frequency with which models require custom code to function and identify those that execute arbitrary Python files during loading. We then apply three complementary static analysis tools: Bandit, CodeQL, and Semgrep, to detect security smells and potential vulnerabilities, categorizing our findings by CWE identifiers to provide a standardized risk taxonomy. We also use YARA to identify malicious patterns and payload signatures. In parallel, we systematically analyze the documentation, API design, and safety mechanisms of each platform to understand their mitigation strategies and enforcement levels. Finally, we conduct a qualitative analysis of over 600 developer discussions from GitHub, Hugging Face, and PyTorch Hub forums, as well as Stack Overflow, to capture community concerns and misconceptions regarding security and usability. Our findings reveal widespread reliance on unsafe defaults, uneven security enforcement across platforms, and persistent confusion among developers about the implications of executing remote code. We conclude with actionable recommendations for designing safer model-sharing infrastructures and striking a balance between usability and security in future AI ecosystems.

Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to mean-centered scalar scores, thereby obscuring distributional structure, cross-dimensional interactions, and worst-case behavior. This paper introduces Social Harm Analysis via Risk Profiles (SHARP), a framework for multidimensional, distribution-aware evaluation of social harm. SHARP models harm as a multivariate random variable and integrates explicit decomposition into bias, fairness, ethics, and epistemic reliability with a union-of-failures aggregation reparameterized as additive cumulative log-risk. The framework further employs risk-sensitive distributional statistics, with Conditional Value at Risk (CVaR95) as a primary metric, to characterize worst-case model behavior. Application of SHARP to eleven frontier LLMs, evaluated on a fixed corpus of n=901 socially sensitive prompts, reveals that models with similar average risk can exhibit more than twofold differences in tail exposure and volatility. Across models, dimension-wise marginal tail behavior varies systematically across harm dimensions, with bias exhibiting the strongest tail severities, epistemic and fairness risks occupying intermediate regimes, and ethical misalignment consistently lower; together, these patterns reveal heterogeneous, model-dependent failure structures that scalar benchmarks conflate. These findings indicate that responsible evaluation and governance of LLMs require moving beyond scalar averages toward multidimensional, tail-sensitive risk profiling.

Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text generation: these APIs expose "gray-box" access leading to new threat vectors. To explore this, we red-team three new functionalities exposed in the GPT-4 APIs: fine-tuning, function calling and knowledge retrieval. We find that fine-tuning a model on as few as 15 harmful examples or 100 benign examples can remove core safeguards from GPT-4, enabling a range of harmful outputs. Furthermore, we find that GPT-4 Assistants readily divulge the function call schema and can be made to execute arbitrary function calls. Finally, we find that knowledge retrieval can be hijacked by injecting instructions into retrieval documents. These vulnerabilities highlight that any additions to the functionality exposed by an API can create new vulnerabilities.

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due to untrusted external tools. While prior work has focused on attacks injected through external tool outputs, we investigate a more fundamental vulnerability: Tool Poisoning, where malicious instructions are embedded within a tool's metadata without execution. To date, this threat has been primarily demonstrated through isolated cases, lacking a systematic, large-scale evaluation. We introduce MCPTox, the first benchmark to systematically evaluate agent robustness against Tool Poisoning in realistic MCP settings. MCPTox is constructed upon 45 live, real-world MCP servers and 353 authentic tools. To achieve this, we design three distinct attack templates to generate a comprehensive suite of 1312 malicious test cases by few-shot learning, covering 10 categories of potential risks. Our evaluation on 20 prominent LLM agents setting reveals a widespread vulnerability to Tool Poisoning, with o1-mini, achieving an attack success rate of 72.8\%. We find that more capable models are often more susceptible, as the attack exploits their superior instruction-following abilities. Finally, the failure case analysis reveals that agents rarely refuse these attacks, with the highest refused rate (Claude-3.7-Sonnet) less than 3\%, demonstrating that existing safety alignment is ineffective against malicious actions that use legitimate tools for unauthorized operation. Our findings create a crucial empirical baseline for understanding and mitigating this widespread threat, and we release MCPTox for the development of verifiably safer AI agents. Our dataset is available at an anonymized repository: https://anonymous.4open.science/r/AAAI26-7C02.

Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinformation that impacts human well-being. Objectives/Methods: We analyzed compliance to requests to generate misleading content about medications in settings where models know the request is illogical. We investigated whether in-context directions and instruction-tuning of LLMs to prioritize logical reasoning over compliance reduced misinformation risk. Results: While all frontier LLMs complied with misinformation requests, both prompt-based and parameter-based approaches can improve the detection of logic flaws in requests and prevent the dissemination of medical misinformation. Conclusion: Shifting LLMs to prioritize logic over compliance could reduce risks of exploitation for medical misinformation.

Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target languages - an approach that converts surface-level linguistic form while failing to reflect the cultural context embedded in threat scenarios, social norms, and legal frameworks. We construct paired DT and culturally-adapted (CA) datasets via 1:1 seed matching for four languages - Korean (KO), Japanese (JA), Thai (TH), and Khmer (KM) - and compare Attack Success Rate (ASR) and Cultural Realism scores across four open-source LLM. CA prompts yield Delta-ASR > 0 across all 16 language x model combinations (mean +9.3 pp), and DT-based evaluation underestimates risk in 44 of 48 category x language combinations. Language-level analysis reveals that the distribution of threat forms is heterogeneous across languages. Cultural Realism analysis further shows that DT Cultural Depth (C3) scores remain consistently below 1.0 out of 3.0 across all four languages (mean 0.17), whereas CA scores reach up to 2.51, indicating that direct translation produces inputs systematically divergent from those encountered in real-world multicultural settings. These findings demonstrate that adapting benchmarks to language-specific cultural contexts - rather than relying on linguistic translation alone - is necessary for valid multilingual LLM safety evaluation.

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional software with AI components entangles novel LLM vulnerabilities with conventional security risks. Existing frameworks only partially address these challenges as they either capture specific vulnerabilities only or require modeling of complete agents. To address these limitations, we introduce threat snapshots: a framework that isolates specific states in an agent's execution flow where LLM vulnerabilities manifest, enabling the systematic identification and categorization of security risks that propagate from the LLM to the agent level. We apply this framework to construct the b^3 benchmark, a security benchmark based on 194331 unique crowdsourced adversarial attacks. We then evaluate 31 popular LLMs with it, revealing, among other insights, that enhanced reasoning capabilities improve security, while model size does not correlate with security. We release our benchmark, dataset, and evaluation code to facilitate widespread adoption by LLM providers and practitioners, offering guidance for agent developers and incentivizing model developers to prioritize backbone security improvements.

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while effective, often depend on input modifications, making them detectable and limiting their stealth and scalability. This paper presents Targeted Model Editing (TME), a novel white-box approach that bypasses safety filters by minimally altering internal model structures while preserving the model's intended functionalities. TME identifies and removes safety-critical transformations (SCTs) embedded in model matrices, enabling malicious queries to bypass restrictions without input modifications. By analyzing distinct activation patterns between safe and unsafe queries, TME isolates and approximates SCTs through an optimization process. Implemented in the D-LLM framework, our method achieves an average Attack Success Rate (ASR) of 84.86% on four mainstream open-source LLMs, maintaining high performance. Unlike existing methods, D-LLM eliminates the need for specific triggers or harmful response collections, offering a stealthier and more effective jailbreak strategy. This work reveals a covert and robust threat vector in LLM security and emphasizes the need for stronger safeguards in model safety alignment.

As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecified objectives). Systematically understanding and benchmarking these risks remains an open challenge. To address this gap, we introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation. We construct an extensible risk taxonomy of 7 categories, which is decomposed into 20 subcategories. ESRRSim generates evaluation scenarios designed to elicit faithful reasoning, paired with dual rubrics assessing both model responses and reasoning traces, in a judge-agnostic and scalable architecture. Evaluation across 11 reasoning LLMs reveals substantial variation in risk profiles (detection rates ranging 14.45%-72.72%), with dramatic generational improvements suggesting models may increasingly recognize and adapt to evaluation contexts.

Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual safety is typically assessed through translation-only benchmarks that preserve the underlying scenario, and empirical evidence of how language and geopolitical context interact remains limited to a narrow set of language pairs. We introduce ROK-FORTRESS https://huggingface.co/datasets/ScaleAI/ROK-FORTRESS_public, a bilingual, culturally adversarial NSPS benchmark that uses the English--Korean language pair and U.S.--ROK geopolitical axis as a case study, separating the effects of language and geopolitical grounding via a transcreation matrix: adversarial intents are evaluated under controlled combinations of (i) English versus Korean language and (ii) U.S.\ versus Korean entities, institutions, and operational details. Each adversarial prompt is paired with a dual-use benign counterpart to quantify over-refusal. Model responses are then scored using calibrated LLM-as-a-judge panels, applying our expert-crafted, prompt-specific binary rubrics. Across a dual-track set of frontier and Korean-optimized models, we find a consistent suppression effect in Korean variants and substantial model-to-model variation in how geopolitical grounding interacts with language. In many models, Korean grounding mitigates the Korean language-driven suppression -- with no model showing significant amplification in the other direction -- indicating that, at least in the English--Korean case, safety behavior is shaped by language-as-risk signals and context interactions that translation-only evaluations miss. The transcreation matrix methodology is designed to generalize to other language--culture pairs.

Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly concerning in real-world deployments, where compromised models may exhibit unpredictable behavior in critical scenarios. Such risks are heightened by the prevalent practice of collecting massive, internet-sourced datasets for training multimodal models, as these datasets may harbor backdoors. Various techniques have been proposed to mitigate the effects of backdooring in multimodal models, such as CleanCLIP, which is the current state-of-the-art approach. In this work, we demonstrate that the efficacy of CleanCLIP in mitigating backdoors is highly dependent on the particular objective used during model pre-training. We observe that stronger pre-training objectives that lead to higher zero-shot classification performance correlate with harder to remove backdoors behaviors. We show this by training multimodal models on two large datasets consisting of 3 million (CC3M) and 6 million (CC6M) datapoints, under various pre-training objectives, followed by poison removal using CleanCLIP. We find that CleanCLIP, even with extensive hyperparameter tuning, is ineffective in poison removal when stronger pre-training objectives are used. Our findings underscore critical considerations for ML practitioners who train models using large-scale web-curated data and are concerned about potential backdoor threats.

Leading language model (LM) providers like OpenAI and Google offer fine-tuning APIs that allow customers to adapt LMs for specific use cases. To prevent misuse, these LM providers implement filtering mechanisms to block harmful fine-tuning data. Consequently, adversaries seeking to produce unsafe LMs via these APIs must craft adversarial training data that are not identifiably harmful. We make three contributions in this context: 1. We show that many existing attacks that use harmless data to create unsafe LMs rely on eliminating model refusals in the first few tokens of their responses. 2. We show that such prior attacks can be blocked by a simple defense that pre-fills the first few tokens from an aligned model before letting the fine-tuned model fill in the rest. 3. We describe a new data-poisoning attack, ``No, Of course I Can Execute'' (NOICE), which exploits an LM's formulaic refusal mechanism to elicit harmful responses. By training an LM to refuse benign requests on the basis of safety before fulfilling those requests regardless, we are able to jailbreak several open-source models and a closed-source model (GPT-4o). We show an attack success rate (ASR) of 57% against GPT-4o; our attack earned a Bug Bounty from OpenAI. Against open-source models protected by simple defenses, we improve ASRs by an average of 3.25 times compared to the best performing previous attacks that use only harmless data. NOICE demonstrates the exploitability of repetitive refusal mechanisms and broadens understanding of the threats closed-source models face from harmless data.

As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly. However, LLM security is a moving target: models produce unpredictable output, are constantly updated, and the potential adversary is highly diverse: anyone with access to the internet and a decent command of natural language. Further, what constitutes a security weak in one context may not be an issue in a different context; one-fits-all guardrails remain theoretical. In this paper, we argue that it is time to rethink what constitutes ``LLM security'', and pursue a holistic approach to LLM security evaluation, where exploration and discovery of issues are central. To this end, this paper introduces garak (Generative AI Red-teaming and Assessment Kit), a framework which can be used to discover and identify vulnerabilities in a target LLM or dialog system. garak probes an LLM in a structured fashion to discover potential vulnerabilities. The outputs of the framework describe a target model's weaknesses, contribute to an informed discussion of what composes vulnerabilities in unique contexts, and can inform alignment and policy discussions for LLM deployment.

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal, where LLMs may reject innocuous prompts and become less helpful. Although the issue of over-refusal has been empirically observed, a systematic measurement is challenging due to the difficulty of crafting prompts that appear harmful but are benign. This study proposes a novel method for automatically generating large-scale sets of "seemingly toxic prompts" (benign prompts likely rejected by LLMs). Leveraging this technique, we introduce OR-Bench, the first large-scale over-refusal benchmark. OR-Bench comprises 80,000 seemingly toxic prompts across 10 common rejection categories, a subset of around 1,000 hard prompts that are challenging even for state-of-the-art LLMs, and an additional 600 toxic prompts to prevent indiscriminate responses. We then conduct a comprehensive study to measure the over-refusal of 25 popular LLMs across 8 model families. Our datasets are available at https://huggingface.co/datasets/bench-llm/or-bench and the demo can be found at https://huggingface.co/spaces/bench-llm/or-bench. We hope this benchmark can help the community develop better safety aligned models.

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of rule-grounded, real-world cases that are essential for robustly protecting LLMs. In this work, we address this critical gap by constructing a comprehensive safety dataset from a compliance perspective. Using a powerful web-searching agent, we collect a rule-grounded, real-world case dataset OmniCompliance-100K, sourced from multi-domain authoritative references. The dataset spans 74 regulations and policies across a wide range of domains, including security and privacy regulations, content safety and user data privacy policies from leading AI companies and social media platforms, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights. In total, our dataset contains 12,985 distinct rules and 106,009 associated real-world compliance cases. Our analysis confirms a strong alignment between the rules and their corresponding cases. We further conduct extensive benchmarking experiments to evaluate the safety and compliance capabilities of advanced LLMs across different model scales. Our experiments reveal several interesting findings that have great potential to offer valuable insights for future LLM safety research.

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn, tool-augmented environments" makes them indispensable. However, ensuring the safety of these agents remains a significant challenge due to the diverse and complex risks arising from dynamic user interactions, external tool usage, and the potential for unintended harmful behaviors. To address this critical issue, we propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation. Concretely, 1) we introduce an open and extensible threat model, OTS, which formalizes how unsafe behaviors emerge from the interplay of user instructions, interaction contexts, and agent actions. This enables precise modeling of safety risks across diverse scenarios. 2) we develop a fully automated data generation pipeline that simulates unsafe user behaviors, applies self-reflective reasoning to generate safe responses, and constructs a large-scale, diverse, and high-quality safety training dataset-eliminating the need for hazardous real-world data collection. To evaluate the effectiveness of our framework, we design comprehensive experiments on both synthetic and real-world safety benchmarks. Results demonstrate that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks, validating the generalization ability of our learned safety strategies. These results highlight the practical advancement and scalability of AutoSafe in building safer LLM-based agents for real-world deployment. We have released the project page at https://auto-safe.github.io/.

While Large Language Models have shown promise in cybersecurity applications, their effectiveness in identifying security threats within cloud deployments remains unexplored. This paper introduces AWS Cloud Security Engineering Eval, a novel dataset for evaluating LLMs cloud security threat modeling capabilities. ACSE-Eval contains 100 production grade AWS deployment scenarios, each featuring detailed architectural specifications, Infrastructure as Code implementations, documented security vulnerabilities, and associated threat modeling parameters. Our dataset enables systemic assessment of LLMs abilities to identify security risks, analyze attack vectors, and propose mitigation strategies in cloud environments. Our evaluations on ACSE-Eval demonstrate that GPT 4.1 and Gemini 2.5 Pro excel at threat identification, with Gemini 2.5 Pro performing optimally in 0-shot scenarios and GPT 4.1 showing superior results in few-shot settings. While GPT 4.1 maintains a slight overall performance advantage, Claude 3.7 Sonnet generates the most semantically sophisticated threat models but struggles with threat categorization and generalization. To promote reproducibility and advance research in automated cybersecurity threat analysis, we open-source our dataset, evaluation metrics, and methodologies.

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an architecture-centric security evaluation that defines 14 trust-boundary attack classes spanning planning, memory, retrieval, tool use, and delegation, and detects failures via *trace-auditable conversation breaks* (unauthorized or unsafe tool use, wrong-principal actions, state/objective integrity violations, and attack-linked deviations). Holding the base model fixed, we evaluate eight agent archetypes under persistent multi-turn interaction and observe substantial architectural variation in mean security break rate (MSBR), ranging from 0.29 pm 0.04 (LangGraph) to 0.51 pm 0.07 (AutoGPT). The highest-risk classes are operational: Denial-of-Wallet (0.62 pm 0.08), Authorization Confusion (0.54 pm 0.10), Retrieval Poisoning (0.47 pm 0.09), and Planning Manipulation (0.44 pm 0.11), while prompt-centric classes remain below 0.20 under standard settings. Breaks are dominated by boundary violations (SIV 31%, WPA 27%, UTI+UTA 24%, ATD 18%), and authorization confusion correlates with objective and tool hijacking (ρapprox 0.63 and ρapprox 0.58). AgentFence reframes agent security around what matters operationally: whether an agent stays within its goal and authority envelope over time.

As large language models (LLMs) continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and categorize the various attacks targeting LLMs, distinguishing between those that occur during the training phase and those that affect already trained models. A thorough analysis of these attacks is presented, alongside an exploration of defense mechanisms designed to mitigate such threats. Defenses are classified into two primary categories: prevention-based and detection-based defenses. Furthermore, our survey summarizes possible attacks and their corresponding defense strategies. It also provides an evaluation of the effectiveness of the known defense mechanisms for the different security threats. Our survey aims to offer a structured framework for securing LLMs, while also identifying areas that require further research to improve and strengthen defenses against emerging security challenges.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.

Computer-use agents extend language models from text generation to sustained interaction with files, terminals, browsers, and external tools. This shift creates safety risks that are difficult to detect from isolated prompts or final responses, because harm often emerges only through multi-step execution traces whose individual actions appear locally benign. We introduce BraveGuard, a self-evolving defense framework for training guard models from open-world threat signals and realistic agent trajectories. BraveGuard mines recent research sources to identify emerging risks and attack patterns, instantiates them as executable computer-use tasks, collects agent rollouts, and derives trajectory-level supervision for guard model training. As new threats and validation failures appear, the pipeline can be repeated, yielding an adaptive defense loop rather than a static, benchmark-driven training process. We instantiate BraveGuard by training multiple guard backbones, including Qwen3-Guard and Llama-Guard variants, and evaluate the resulting guards on trajectory-level agent-safety benchmarks. BraveGuard consistently improves safety detection across computer-use trajectories. On AgentHazard, it substantially improves detection accuracy over off-the-shelf guard models, with accuracy increasing from 38.79% to 82.38% under the averaged guard-model setting. These results show that guard supervision grounded in open-world threat discovery and realistic agent execution can improve safety monitoring beyond fixed taxonomies and synthetic prompt-level data. BraveGuard offers a scalable path toward adaptive defenses for computer-use agents facing evolving real-world risks.

Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However, this over-optimization often prioritizes compliance, making models vulnerable to harmful prompts. To mitigate this safety degradation, recent approaches rely on external teacher distillation, yet this introduces a distributional discrepancy that degrades native reasoning. We propose ThinkSafe, a self-generated alignment framework that restores safety alignment without external teachers. Our key insight is that while compliance suppresses safety mechanisms, models often retain latent knowledge to identify harm. ThinkSafe unlocks this via lightweight refusal steering, guiding the model to generate in-distribution safety reasoning traces. Fine-tuning on these self-generated responses effectively realigns the model while minimizing distribution shift. Experiments on DeepSeek-R1-Distill and Qwen3 show ThinkSafe significantly improves safety while preserving reasoning proficiency. Notably, it achieves superior safety and comparable reasoning to GRPO, with significantly reduced computational cost. Code, models, and datasets are available at https://github.com/seanie12/ThinkSafe.git.

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from acting on user-provided content. Existing studies on agent security largely focus on model-internal vulnerabilities or adversarial access to agent interfaces, overlooking attacks that exploit users as unintended conduits. In this paper, we study user-mediated attacks, where benign users are tricked into relaying untrusted or attacker-controlled content to agents, and analyze how commercial LLM agents respond under such conditions. We conduct a systematic evaluation of 12 commercial agents in a sandboxed environment, covering 6 trip-planning agents and 6 web-use agents, and compare agent behavior across scenarios with no, soft, and hard user-requested safety checks. Our results show that agents are too helpful to be safe by default. Without explicit safety requests, trip-planning agents bypass safety constraints in over 92% of cases, converting unverified content into confident booking guidance. Web-use agents exhibit near-deterministic execution of risky actions, with 9 out of 17 supported tests reaching a 100% bypass rate. Even when users express soft or hard safety intent, constraint bypass remains substantial, reaching up to 54.7% and 7% for trip-planning agents, respectively. These findings reveal that the primary issue is not a lack of safety capability, but its prioritization. Agents invoke safety checks only conditionally when explicitly prompted, and otherwise default to goal-driven execution. Moreover, agents lack clear task boundaries and stopping rules, frequently over-executing workflows in ways that lead to unnecessary data disclosure and real-world harm.

U.S. national security customers have begun to utilize large language models, including enterprise versions of ``off-the-shelf'' models (e.g., ChatGPT) familiar to the public. This uptake will likely accelerate. However, recent studies suggest that off-the-shelf large language models frequently suggest escalatory actions when prompted with geopolitical or strategic scenarios. We demonstrate two simple, non-technical interventions to control these tendencies. Introducing these interventions into the experimental wargame design of a recent study, we substantially reduce escalation throughout the game. Calls to restrict the use of large language models in national security applications are thus premature. The U.S. government is already, and will continue, employing large language models for scenario planning and suggesting courses of action. Rather than warning against such applications, this study acknowledges the imminent adoption of large language models, and provides actionable measures to align them with national security goals, including escalation management.

Large Language Models (LLMs) are increasingly deployed as computer-use agents, autonomously performing tasks within real desktop or web environments. While this evolution greatly expands practical use cases for humans, it also creates serious security exposures. We present SUDO (Screen-based Universal Detox2Tox Offense), a novel attack framework that systematically bypasses refusal-trained safeguards in commercial computer-use agents, such as Claude for Computer Use. The core mechanism, Detox2Tox, transforms harmful requests (that agents initially reject) into seemingly benign requests via detoxification, secures detailed instructions from advanced vision language models (VLMs), and then reintroduces malicious content via toxification just before execution. Unlike conventional jailbreaks, SUDO iteratively refines its attacks based on a built-in refusal feedback, making it increasingly effective against robust policy filters. In extensive tests spanning 50 real-world tasks and multiple state-of-the-art VLMs, SUDO achieves a stark attack success rate of 24.41% (with no refinement), and up to 41.33% (by its iterative refinement) in Claude for Computer Use. By revealing these vulnerabilities and demonstrating the ease with which they can be exploited in real-world computing environments, this paper highlights an immediate need for robust, context-aware safeguards. WARNING: This paper includes harmful or offensive model outputs

Large language models (LLMs) are typically aligned to comply with safety guidelines by refusing harmful instructions. A recent attack, termed abliteration, isolates and suppresses the single latent direction most responsible for refusal behavior, enabling the model to generate unethical content. We propose a defense that modifies how models generate refusals. We construct an extended-refusal dataset that contains harmful prompts with a full response that justifies the reason for refusal. We then fine-tune Llama-2-7B-Chat and Qwen2.5-Instruct (1.5B and 3B parameters) on our extended-refusal dataset, and evaluate the resulting systems on a set of harmful prompts. In our experiments, extended-refusal models maintain high refusal rates, dropping at most by 10%, whereas baseline models' refusal rates drop by 70-80% after abliteration. A broad evaluation of safety and utility shows that extended-refusal fine-tuning neutralizes the abliteration attack while preserving general performance.

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle manipulations within the embedding layer. This work identifies a novel class of deployment phase attacks that exploit this vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text. These perturbations, though statistically benign, systematically bypass safety alignment mechanisms and induce harmful behaviors during inference. We propose Search based Embedding Poisoning(SEP), a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens. SEP leverages a predictable linear transition in model responses, from refusal to harmful output to semantic deviation to identify a narrow perturbation window that evades alignment safeguards. Evaluated across six aligned LLMs, SEP achieves an average attack success rate of 96.43% while preserving benign task performance and evading conventional detection mechanisms. Our findings reveal a critical oversight in deployment security and emphasize the urgent need for embedding level integrity checks in future LLM defense strategies.

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural language responses, their efficacy remains largely unexplored within multi-step tool-use trajectories. To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety. It encompasses 12 risk categories, ranging from security threats (e.g., prompt injection, privacy leaks) to operational failures (e.g., hallucinations, interface inconsistencies), featuring over 1,000 unique execution instances. Our evaluation of 13 LLM-as-a-guard models and 7 specialized guardrails yields three critical findings: 1) Structural Bottleneck: Guardrail efficacy is driven more by structural data competence (e.g., JSON parsing) than semantic safety alignment. Performance correlates strongly with structured-to-text benchmarks (ρ=0.79) but shows near-zero correlation with standard jailbreak robustness. 2) Architecture over Scale: Model architecture influences risk detection performance more significantly than model size, with general-purpose LLMs consistently outperforming specialized safety guardrails in trajectory analysis. 3) Temporal Stability: Accuracy remains resilient across extended trajectories. Increased execution steps allow models to pivot from static tool definitions to dynamic execution behaviors, actually improving risk detection performance in later stages. Our findings suggest that securing agentic workflows requires jointly optimizing for structural reasoning and safety alignment to effectively mitigate mid-trajectory risks.

Large language models (LLMs) are typically aligned to a universal set of safety and usage principles intended for broad public acceptability. Yet, real-world applications of LLMs often take place within organizational ecosystems shaped by distinctive corporate policies, regulatory requirements, use cases, brand guidelines, and ethical commitments. This reality highlights the need for rigorous and comprehensive evaluation of LLMs with pluralistic alignment goals, an alignment paradigm that emphasizes adaptability to diverse user values and needs. In this work, we present PLURALISTIC BEHAVIOR SUITE (PBSUITE), a dynamic evaluation suite designed to systematically assess LLMs' capacity to adhere to pluralistic alignment specifications in multi-turn, interactive conversations. PBSUITE consists of (1) a diverse dataset of 300 realistic LLM behavioral policies, grounded in 30 industries; and (2) a dynamic evaluation framework for stress-testing model compliance with custom behavioral specifications under adversarial conditions. Using PBSUITE, We find that leading open- and closed-source LLMs maintain robust adherence to behavioral policies in single-turn settings (less than 4% failure rates), but their compliance weakens substantially in multi-turn adversarial interactions (up to 84% failure rates). These findings highlight that existing model alignment and safety moderation methods fall short in coherently enforcing pluralistic behavioral policies in real-world LLM interactions. Our work contributes both the dataset and analytical framework to support future research toward robust and context-aware pluralistic alignment techniques.

Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware. While LLM quantization's impact on utility has been extensively explored, this work for the first time studies its adverse effects from a security perspective. We reveal that widely used quantization methods can be exploited to produce a harmful quantized LLM, even though the full-precision counterpart appears benign, potentially tricking users into deploying the malicious quantized model. We demonstrate this threat using a three-staged attack framework: (i) first, we obtain a malicious LLM through fine-tuning on an adversarial task; (ii) next, we quantize the malicious model and calculate constraints that characterize all full-precision models that map to the same quantized model; (iii) finally, using projected gradient descent, we tune out the poisoned behavior from the full-precision model while ensuring that its weights satisfy the constraints computed in step (ii). This procedure results in an LLM that exhibits benign behavior in full precision but when quantized, it follows the adversarial behavior injected in step (i). We experimentally demonstrate the feasibility and severity of such an attack across three diverse scenarios: vulnerable code generation, content injection, and over-refusal attack. In practice, the adversary could host the resulting full-precision model on an LLM community hub such as Hugging Face, exposing millions of users to the threat of deploying its malicious quantized version on their devices.

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order to measure the latent propensity of LLM agents for taking illegal actions under an EU legislative context, we introduce EU-Agent-Bench, a verifiable human-curated benchmark that evaluates an agent's alignment with EU legal norms in situations where benign user inputs could lead to unlawful actions. Our benchmark spans scenarios across several categories, including data protection, bias/discrimination, and scientific integrity, with each user request allowing for both compliant and non-compliant execution of the requested actions. Comparing the model's function calls against a rubric exhaustively supported by citations of the relevant legislature, we evaluate the legal compliance of frontier LLMs, and furthermore investigate the compliance effect of providing the relevant legislative excerpts in the agent's system prompt along with explicit instructions to comply. We release a public preview set for the research community, while holding out a private test set to prevent data contamination in evaluating upcoming models. We encourage future work extending agentic safety benchmarks to different legal jurisdictions and to multi-turn and multilingual interactions. We release our code on https://github.com/ilijalichkovski/eu-agent-bench{this URL}.

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their vulnerabilities and safety have arisen, which can pose challenges to their deployment and application in real-world settings. This paper presents a comprehensive survey of LRMs, meticulously exploring and summarizing the newly emerged safety risks, attacks, and defense strategies. By organizing these elements into a detailed taxonomy, this work aims to offer a clear and structured understanding of the current safety landscape of LRMs, facilitating future research and development to enhance the security and reliability of these powerful models.

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.

Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety-critical system, instantiated in a simulated nuclear power plant control room. A five-role operator team, each backed by a configurable LLM, runs a plant governed by six critical safety functions (CSFs), while adversaries inject messages over four channels in bounded multi-turn sessions with per-turn feedback. Harm is an objective signal rather than LLM-judged text: a run terminates the moment any CSF is lost, attributed to the causing message. Evaluating four frontier operator models under a fixed-attack paired-replay protocol, we find that adaptive multi-turn attacks reliably push the operator team past a safety limit: across the four models, between 8.7% and 12.1% of attack sessions end with the plant losing a critical safety function. Although the four models look almost equally robust by this aggregate rate, their failures barely overlap: of 149 sessions, none defeat all four models while a third defeat at least one, so vulnerabilities are nearly disjoint across models rather than nested. The effect of added defences is strongly model-dependent: the same guardrail stack or safety-advisor agent that lowers attack success for one model can raise it for another. We release the simulation venue, attack dataset, and replay tooling for reproducible safety evaluation of LLM agents.

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It defines security boundaries, authenticates prompts, applies security rules and custom policies, and controls agentic behavior, enabling a defense-in-depth strategy. The A2AS framework avoids latency overhead, external dependencies, architectural changes, model retraining, and operational complexity. The BASIC security model is introduced as the A2AS foundation: (B) Behavior certificates enable behavior enforcement, (A) Authenticated prompts enable context window integrity, (S) Security boundaries enable untrusted input isolation, (I) In-context defenses enable secure model reasoning, (C) Codified policies enable application-specific rules. This first paper in the series introduces the BASIC security model and the A2AS framework, exploring their potential toward establishing the A2AS industry standard.

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face of varying social norms across cultures and regions. In addition, users may have diverse safety needs, making a model with static safety standards too restrictive to be useful, as well as too costly to be re-aligned. We propose Controllable Safety Alignment (CoSA), a framework designed to adapt models to diverse safety requirements without re-training. Instead of aligning a fixed model, we align models to follow safety configs -- free-form natural language descriptions of the desired safety behaviors -- that are provided as part of the system prompt. To adjust model safety behavior, authorized users only need to modify such safety configs at inference time. To enable that, we propose CoSAlign, a data-centric method for aligning LLMs to easily adapt to diverse safety configs. Furthermore, we devise a novel controllability evaluation protocol that considers both helpfulness and configured safety, summarizing them into CoSA-Score, and construct CoSApien, a human-authored benchmark that consists of real-world LLM use cases with diverse safety requirements and corresponding evaluation prompts. We show that CoSAlign leads to substantial gains of controllability over strong baselines including in-context alignment. Our framework encourages better representation and adaptation to pluralistic human values in LLMs, and thereby increasing their practicality.

As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed that LLMs often fail to grasp the notion of safe behaviors, resulting in either unjustified refusals to harmless prompts or the generation of harmful content. While substantial efforts have been made to improve their robustness, existing defenses often rely on costly fine-tuning of model parameters or employ suboptimal heuristic techniques. In this work, we take a novel approach to safeguard LLMs by learning to adapt the system prompts in instruction-tuned LLMs. While LLMs are typically pre-trained to follow a fixed system prompt, we investigate the impact of tailoring the system prompt to each specific user input on the safety of the responses. To this end, we propose Sysformer, a transformer model that updates an initial system prompt to a more robust system prompt in the LLM input embedding space while attending to the user prompt. While keeping the LLM parameters frozen, the Sysformer is trained to refuse to respond to a set of harmful prompts while responding ideally to a set of safe ones. Through extensive experiments on 5 LLMs from different families and 2 recent benchmarks, we demonstrate that Sysformer can significantly enhance the robustness of LLMs, leading to upto 80% gain in the refusal rate on harmful prompts while enhancing the compliance with the safe prompts by upto 90%. Results also generalize well to sophisticated jailbreaking attacks, making LLMs upto 100% more robust against different attack strategies. We hope our findings lead to cheaper safeguarding of LLMs and motivate future investigations into designing variable system prompts.

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies, appropriately refusing any request that would violate them, while still maintaining a helpful and natural interaction. This calls for the development of tailored design and evaluation methodologies to ensure agent resilience against malicious user behavior. We propose a novel threat model that focuses on adversarial users aiming to exploit policy-adherent agents for personal benefit. To address this, we present CRAFT, a multi-agent red-teaming system that leverages policy-aware persuasive strategies to undermine a policy-adherent agent in a customer-service scenario, outperforming conventional jailbreak methods such as DAN prompts, emotional manipulation, and coercive. Building upon the existing tau-bench benchmark, we introduce tau-break, a complementary benchmark designed to rigorously assess the agent's robustness against manipulative user behavior. Finally, we evaluate several straightforward yet effective defense strategies. While these measures provide some protection, they fall short, highlighting the need for stronger, research-driven safeguards to protect policy-adherent agents from adversarial attacks

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom available to adversaries in the real world. In particular, with strong verifiers and financial incentives, agents for offensive cybersecurity are amenable to iterative improvement by would-be adversaries. We argue that assessments should take into account an expanded threat model in the context of cybersecurity, emphasizing the varying degrees of freedom that an adversary may possess in stateful and non-stateful environments within a fixed compute budget. We show that even with a relatively small compute budget (8 H100 GPU Hours in our study), adversaries can improve an agent's cybersecurity capability on InterCode CTF by more than 40\% relative to the baseline -- without any external assistance. These results highlight the need to evaluate agents' cybersecurity risk in a dynamic manner, painting a more representative picture of risk.

Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems. While extensive effort has gone into empirical mitigations, the evolving nature of attacks and the complexity of data require a more principled, provable approach to robustly learn on such data - and to understand how perturbations influence the final model. Hence, we introduce MIBP-Cert, a novel certification method based on mixed-integer bilinear programming (MIBP) that computes sound, deterministic bounds to provide provable robustness even under complex threat models. By computing the set of parameters reachable through perturbed or manipulated data, we can predict all possible outcomes and guarantee robustness. To make solving this optimization problem tractable, we propose a novel relaxation scheme that bounds each training step without sacrificing soundness. We demonstrate the applicability of our approach to continuous and discrete data, as well as different threat models - including complex ones that were previously out of reach.

AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer around them is actually safe. That literature is scattered. Papers on sandbox isolation, capability and access control, policy enforcement, time-of-check-to-time-of-use (TOCTOU) races, Model Context Protocol (MCP) threats, identity delegation, execution provenance, network egress control, and static analysis of agent-generated code are published independently and rarely cite one another. We systematize 39 papers published between 2023 and 2026 into 17 categories, each verified directly against its source. The same verification protocol also confirms four disclosed, patched CVEs directly affecting production agent harnesses. Reading across categories surfaces five cross-cutting gaps that no single paper addresses. (1) Isolation architectures and capability models are almost never evaluated against one another on a shared benchmark. (2) Policy-enforcement studies report failure rates from 69% to 98% of real denylists, yet no isolation paper re-evaluates its own defense under that adversarial setting. (3) TOCTOU and MCP threats are analyzed as separate literatures despite both being instances of the same state-validation problem. (4) Every enforcement mechanism assumes an honest policy author, leaving policy-authoring error itself unaddressed. (5) Benign but out-of-scope agent actions occurring at rates up to 17.1% under realistic prompting are addressed by no access-control or capability paper in the corpus. Existing broader surveys of agentic AI security discuss sandboxing only as one item among many defenses, leaving execution security without a dedicated systematization. This paper is written to fill that gap. We conclude with a research agenda directed at the five gaps.