进退维谷：大型语言模型中伦理推理与安全对齐之间的张力
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
AI总结：
本文提出TRIAL多轮红队方法，通过将有害请求嵌入伦理框架来利用模型伦理推理能力，并引入ERR防御框架（分层有害门控LoRA架构）以区分工具性回应与解释性回应，实现鲁棒防御。
摘要：
大型语言模型的安全对齐主要基于二元假设，即请求要么安全要么不安全。当模型遇到伦理困境时，这种分类被证明是不充分的，因为通过道德权衡进行推理的能力创造了一个独特的攻击面。我们通过TRIAL（一种多轮红队方法）形式化了这一漏洞，该方法将有害请求嵌入伦理框架中。TRIAL通过系统性地利用模型的伦理推理能力，将有害行为描述为道德上必要的妥协，在大多数测试模型上实现了高攻击成功率。基于这些见解，我们引入了ERR（伦理推理鲁棒性），一种防御框架，区分了导致有害结果的工具性回应和分析伦理框架而不认可有害行为的解释性回应。ERR采用分层有害门控LoRA架构，在保持模型实用性的同时，实现了对基于推理的攻击的鲁棒防御。
英文摘要：
Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves high attack success rates across most tested models by systematically exploiting the model's ethical reasoning capabilities to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.
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。
