道德博弈:利用道德基础理论突破大语言模型的安全护栏
Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs
AI总结:
该研究基于道德基础理论构建多智能体框架,可通过道德化处理让大语言模型绕过安全护栏,在多个模型和数据集上验证了其有效性,且发现安全基准存在道德基础不平衡的问题。
摘要:
社会心理学长期以来描述了人们如何被说服将有害行为解读为道德行为。近期研究表明,大语言模型(LLMs)会反映人类心理学的多个方面,从认知偏差到社会从众性。这提出了一个具有直接安全影响的问题:能否通过道德化处理让LLMs绕过安全护栏?我们基于道德基础理论(MFT)构建了一个多智能体框架来回答该问题。对于最初被拒绝的有害请求,我们的智能体首先诊断该提示违反了哪一种道德基础(MF),然后确定一种可使同一请求显得合乎道德的正当基础,据此重写提示,并通过生成具有类似道德重构的先例来强化该提示。我们在三个知名越狱数据集的有害提示上,对五个开源和专有模型评估了该框架。分析显示,模型对道德化处理高度敏感,单次尝试的越狱率很高,多次尝试下成功率进一步提升。我们还发现,安全基准在其违反的道德基础上存在不平衡,集中于模型已表现出偏差的那些基础。
英文摘要:
Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language Models (LLMs) echo aspects of human psychology, from cognitive biases to social conformity. This raises a question with direct safety implications: can LLMs be moralized to bypass safety guardrails? We answer this question with a multi-agent framework grounded in Moral Foundations Theory (MFT). Given a harmful request that is initially refused, our agents diagnose which moral foundation (MF) the prompt is violating, identify a justifiable foundation under which the same request appears virtuous, rewrite the prompt accordingly, and reinforce it with generated precedents of comparable moral reframing. We evaluate our framework on harmful prompts from three well-known jailbreak datasets across five open-source and proprietary models. Our analysis reveals that models are highly susceptible to moralization, exhibiting high single-trial jailbreak rates with success increasing further under repeated attempts. We also find that safety benchmarks are imbalanced in the MFs they violate, concentrating on foundations toward which models already exhibit biases.
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。