LLMs are known to be vulnerable to jailbreak attacks, even after safety alignment. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses that are rooted in the same harmful knowledge (e.g., detailed steps to make a bomb). Therefore, we conjecture that directly unlearn the harmful knowledge in the LLM can be a more effective way to defend against jailbreak attacks than the mainstream supervised fine-tuning (SFT) based approaches. Our extensive experiments confirmed our insight and suggested surprising generalizability of our unlearning-based approach: using only 20 raw harmful questions \emph{without} any jailbreak prompt during training, our solution reduced the Attack Success Rate (ASR) in Vicuna-7B on \emph{out-of-distribution} (OOD) harmful questions wrapped with various complex jailbreak prompts from 82.6\% to 7.7\%. This significantly outperforms Llama2-7B-Chat, which is fine-tuned on about 0.1M safety alignment samples but still has an ASR of 21.9\% even under the help of an additional safety system prompt. Further analysis reveals that the generalization ability of our solution stems from the intrinsic relatedness among harmful responses across harmful questions (e.g., response patterns, shared steps and actions, and similarity among their learned representations in the LLM). Our code is available at \url{https://github.com/thu-coai/SafeUnlearning}.

将有害知识在LLM中直接取消学习是一种有效防御越狱攻击的方法，实验证实其具有意外的普适性，将攻击成功率从82.6％降低到7.7％。

安全的消去学习：一个出人意料地有效且具有普适性的解决方案，用于防御越狱攻击