garak

【数据与研究】Security testing and red-teaming for LLMs using NVIDIA's garak vulnerability scanner. Use when probing AI models for jailbreaks, prompt injections, data leakage, toxic content generation, or other failure modes. Triggers on "test LLM security", "red team model", "run garak", "LLM vulnerability scan", "jailbreak testing", or "prompt injection test".

独立 GitHub 快照 · 自动分类 · 以原作者文档为准