secbert-redhat-data

This is a fine-tuned secbert model, using Red Hat public security data from: https://huggingface.co/datasets/huzaifas-sidhpurwala/RedHat-security-VeX

Model Details

Model Description

• Developed by: Huzaifa Sidhpurwala huzaifas@redhat.com
• Model type: Text classification
• License: Apache 2.0

Highlights

This model is trained with the summary, description and severity fields from https://huggingface.co/datasets/huzaifas-sidhpurwala/RedHat-security-VeX

The aim here is given the description of a security issue, the model should correct be able to estimate the severity level of the security issue in accordance with the standards documented at: https://access.redhat.com/security/updates/classification

How to Get Started with the Model

A minimal inference code is available at: https://github.com/sidhpurwala-huzaifa/redhat-sev-classifier/blob/main/inference/

Model Card Contact

Huzaifa Sidhpurwala - huzaifas@redhat.com