⚡Megatron LLM Hub
←Back to search
Twitter

开源仓库 jailbreak-eval-7llms 提供七个大模型越狱攻击与防御的系统评测代码

可直接复跑越狱与防御基线,用于自建 Agent 的红队评估。
llm越狱工具报告
jailbreak-eval-7llms — Code for "Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models" https://t.co/HxbQcqybaf https://t.co/Hfjsknp0TT