CS-Guard: Benchmarking LLM Guardrails for Code Generation Security
CS-Guard, the first benchmark to systematically evaluate guardrails for code generation security, finds that current guardrails perform poorly against malicious code-generation re- quests, and uses a modular three-layer guardrail taxonomy that lets developers register guardrails for evaluation.
Jinyang Li, Ming-Yu Guo, Hung X. Nguyen
· 0 citations