通过安全知识神经元揭开大语言模型劫持的面纱
Unraveling LLM Jailbreaks Through Safety Knowledge Neurons
AI总结：
本文提出SafeTuning方法，通过调整安全知识神经元激活来提升大语言模型对劫持攻击的防御能力，实验显示其在多个模型上均有效
摘要：
大型语言模型（LLMs）在各种应用中日益受到关注。然而，随着一些用户试图利用这些模型进行恶意目的，如合成受控物质和传播虚假信息，一种被称为“劫持”的技术引起了广泛关注。尽管一些研究通过修改输出分布或检测有害内容来防御劫持攻击，但其确切原因仍不明确。在本工作中，我们提出了一种新的神经元层面可解释性方法，专注于安全相关知识神经元的作用。与现有方法不同，我们的方法将模型的内部表示投影到更一致和可解释的词汇空间中。我们随后展示，调整安全相关神经元的激活可以有效地控制模型的行为，其平均ASR高于97%。基于这一见解，我们提出了SafeTuning，一种增强安全关键神经元的微调策略，以提高模型对劫持的鲁棒性。SafeTuning在多个LLM上一致地降低了攻击成功率，并优于所有四个基线防御。这些发现为理解和防御劫持攻击提供了新的视角。
英文摘要：
Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled substances and the propagation of disinformation, a technique known as "Jailbreak." While some studies have achieved defenses against jailbreak attacks by modifying output distributions or detecting harmful content, the exact rationale still remains elusive. In this work, we present a novel neuron-level interpretability method that focuses on the role of safety-related knowledge neurons. Unlike existing approaches, our method projects the model's internal representation into a more consistent and interpretable vocabulary space. We then show that adjusting the activation of safety-related neurons can effectively control the model's behavior with a mean ASR higher than 97%. Building on this insight, we propose SafeTuning, a fine-tuning strategy that reinforces safety-critical neurons to improve model robustness against jailbreaks. SafeTuning consistently reduces attack success rates across multiple LLMs and outperforms all four baseline defenses. These findings offer a new perspective on understanding and defending against jailbreak attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
