Skip to main content
Purple Llama Logo

CyberSecEval 4

Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

CyberSecEval 4

This version introduces AutoPatchBench, a benchmark that measures an LLM agent's capability to automatically patch security vulnerabilities in native code.

Prompt Guard

Prompt Guard is a new model for guardrailing LLM inputs against prompt attacks - in particular jailbreaking techniques and indirect injections embedded into third party data. For more information, see our Model card.