LLM vulnerability patching skills remain limited

Security teams are wondering whether LLMs can help speed up patching. A new study tests that idea and shows where the tools hold up and where they fall short. The researchers tested LLMs from OpenAI, Meta, DeepSeek, and Mistral to see how well they could fix vulnerable Java functions in a single attempt. A broad mix of models put through the same trial The study examined two groups of vulnerabilities. The first consisted of authentic … More →

The post LLM vulnerability patching skills remain limited appeared first on Help Net Security.