HarmTransform: 通过多智能体辩论将显性有害查询转化为隐蔽形式
HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate
AI总结：
HarmTransform通过多智能体辩论框架，系统地将有害查询转化为隐蔽形式，以提升大型语言模型的安全对齐能力。
摘要：
大型语言模型（LLMs）配备了安全机制来检测和阻止有害查询，但当前对齐方法主要关注显而易见的危险内容，而忽视了更微妙的威胁。然而，用户可以通过隐蔽的改写来伪装有害意图，以保持恶意目标的同时显得无害，这在现有安全训练数据中存在显著缺口。为了解决这一限制，我们引入了HarmTransform，一种多智能体辩论框架，用于系统地将有害查询转化为更隐蔽的形式，同时保持其底层有害意图。我们的框架利用多个智能体之间的迭代批评和改进，生成高质量、隐蔽的有害查询转换，可用于改进未来的LLM对齐。实验表明，HarmTransform在生成有效的查询转换方面显著优于标准基线。同时，我们的分析发现，辩论是一种双刃剑：虽然它可以增强转换并提高隐蔽性，但也可能引入话题转换和不必要的复杂性。这些见解突显了多智能体辩论在生成全面安全训练数据方面的潜力和局限性。
英文摘要：
Large language models (LLMs) are equipped with safety mechanisms to detect and block harmful queries, yet current alignment approaches primarily focus on overtly dangerous content and overlook more subtle threats. However, users can often disguise harmful intent through covert rephrasing that preserves malicious objectives while appearing benign, which creates a significant gap in existing safety training data. To address this limitation, we introduce HarmTransform, a multi-agent debate framework for systematically transforming harmful queries into stealthier forms while preserving their underlying harmful intent. Our framework leverages iterative critique and refinement among multiple agents to generate high-quality, covert harmful query transformations that can be used to improve future LLM safety alignment. Experiments demonstrate that HarmTransform significantly outperforms standard baselines in producing effective query transformations. At the same time, our analysis reveals that debate acts as a double-edged sword: while it can sharpen transformations and improve stealth, it may also introduce topic shifts and unnecessary complexity. These insights highlight both the promise and the limitations of multi-agent debate for generating comprehensive safety training data.
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。
