通过重学习神经元让大模型放弃安全约束，暴露对微调攻击的脆弱性。
NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
- 分析有害与无害输入下的神经元激活模式，定位安全关键神经元。
- 仅用少量微调即成功移除安全限制，实现对有害内容的生成。
- 揭示当前对齐机制的缺陷，适合研究模型安全与对抗攻击者参考。
大型语言模型的安全对齐依赖于微调机制以调控神经元激活，从而抑制有害内容。本文提出一种新方法，通过识别并修改负责安全约束的神经元来诱导对齐失效。该方法包含三个步骤：神经元激活分析，考察模型在有害与无害提示下的激活模式，以识别对区分有害与无害输入至关重要的神经元；基于相似性的神经元识别，系统定位承担安全对齐功能的神经元；神经元重学习以移除安全限制，对选定神经元进行微调，恢复模型生成此前被禁止响应的能力。实验表明，本方法在极少微调条件下即可有效解除安全约束，凸显当前对齐技术的关键漏洞。研究结果强调了防范针对大模型对抗性微调攻击的必要性。
原文摘要 · Abstract (English)
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and modifying the neurons responsible for safety constraints. Our method consists of three key steps: Neuron Activation Analysis, where we examine activation patterns in response to harmful and harmless prompts to detect neurons that are critical for distinguishing between harmful and harmless inputs; Similarity-Based Neuron Identification, which systematically locates the neurons responsible for safe alignment; and Neuron Relearning for Safety Removal, where we fine-tune these selected neurons to restore the model's ability to generate previously restricted responses. Experimental results demonstrate that our method effectively removes safety constraints with minimal fine-tuning, highlighting a critical vulnerability in current alignment techniques. Our findings underscore the need for robust defenses against adversarial fine-tuning attacks on LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。