Jailbreak attack datasets generated against multiple LLMs, one dataset per attack method.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 8
deepkeep-ai/sae-guard-gemma3-4b-multilingual-korean-2-june
Text Classification • 0.2B • Updated • 36
deepkeep-ai/openai-privacy-filter
Token Classification • 1B • Updated • 74
deepkeep-ai/stable-diffusion-xl-1.0-inpainting-0.1-9
1 • Updated • 96
deepkeep-ai/napguard-patch-detector-3
7.04M • Updated • 99
deepkeep-ai/sac-patch-segmenter-2
1.08M • Updated • 105
deepkeep-ai/Ministral-3-8B-Instruct-2512
9B • Updated • 20k
deepkeep-ai/sae-guard-gemma3-4b-english-expanded
Image Feature Extraction • 1 • Updated • 2
deepkeep-ai/sae-guard-gemma3-4b-english-research
Image Feature Extraction • 1 • Updated • 5 • 1
datasets 8
deepkeep-ai/semantic-encoding-data-splits-llm-korean
Viewer • Updated • 16.5k • 69
deepkeep-ai/jigsaw_toxic_not_harmful_5k
Viewer • Updated • 5k • 9
deepkeep-ai/jigsaw_toxic_not_harmful_5k_translated
Viewer • Updated • 5k • 14
deepkeep-ai/notinject_expanded_1k_qwen35_9b_cuda_translated_roleplay
Viewer • Updated • 1k • 109
deepkeep-ai/seq_cls_train_translated_v3
Viewer • Updated • 2.15k • 7
deepkeep-ai/datasets
Updated • 2
deepkeep-ai/AdvBench-gcg
Viewer • Updated • 268 • 10
deepkeep-ai/benchoverflow
Viewer • Updated • 2.98k • 5