arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.07968cs.CR
收藏

从守护者到魔鬼?由LLM防御引发的意外风险交互

One Risk Down, Another Up: Cross-Risk Interactions Induced by LLM Defenses

Shandong University(山东大学);Tsinghua University(清华大学)

Xiangtao Meng, Tianshuo Cong, Li Wang, Wenyu Chen, Zheng Li, Shanqing Guo, Xiaoyun Wang

AI总结:

本文提出CrossRiskEval框架,系统研究LLM防御在安全、公平性与隐私间的相互影响,揭示防御措施对其他风险的非随机交互机制。

摘要:

大型语言模型(LLMs)在各种应用中展现出卓越的性能,但其在现实世界中的部署面临诸多风险,包括 jailbreak 攻击和隐私泄露。为减轻这些风险,已经提出了许多防御策略。然而,大多数现有研究将这些防御措施孤立评估,并忽略了它们对其他风险维度的影响。在本工作中,我们引入了一种新的跨风险评估范式,并首次探讨了LLM中防御之间的意外交互。具体来说,我们关注安全、公平性和隐私之间的相互作用。为此,我们提出了CrossRiskEval,一个系统地刻画防御针对一个风险(例如安全)如何影响其他风险(例如公平性或隐私)的框架。我们对14个部署了防御的LLM进行了广泛的实证研究和机理分析,涵盖了12种防御策略。我们的结果表明,针对单一风险的防御往往会对其他风险产生可测量的影响。这些影响在模型、任务和防御策略等不同因素下方向和幅度各异,并且在风险对之间往往存在不对称性。此外,我们的机理分析表明,这些交互并非随机:它们源于冲突缠绕的神经元,这些是共享的内部表示,对不同风险有相反的贡献。调整一个风险因此会扰动这些表示,并导致非目标风险的系统性变化。这些发现揭示了单一风险评估的局限性,并强调了在设计和部署LLM防御时需要整体性和交互意识评估的必要性。

英文摘要:

Large Language Models (LLMs) are increasingly deployed in high-stakes settings, where they face diverse risks. Numerous defense strategies have been proposed to mitigate these risks, but they are almost always evaluated in isolation. This isolated view leaves a critical question open: does mitigating one risk inadvertently change a model's exposure to others? Beyond the well-studied risk-utility trade-off, we present the first systematic study of cross-risk interactions induced by LLM defenses. We propose CrossRiskEval, an evaluation paradigm that situates a defended model in a multi-dimensional risk space and quantifies how a defense built for one risk shifts the others. Among 166 cross-risk evaluations covering 32 defended models, 77.1% exhibit statistically significant cross-risk interactions. Most of these interactions amplify non-target risks, with increases exceeding 100% in some cases. Beyond behavioral evaluation, we conduct neuron-level analyses in seven selected cases to investigate one possible pathway associated with these interactions. We identify conflict-entangled neurons whose activation interventions produce opposing effects on proxies for the target and non-target risks. In conflict cases, restoring these neurons to their base-model activations partially reduces the corresponding risk increases, providing evidence that defense-induced changes to these neurons may contribute to the observed interactions. Building on this evidence, we propose Conflict-Aware Freezing, a training-time strategy that prevents direct updates to the parameters associated with the identified neurons. Across five conflict cases, it offsets 35%-196% of non-target risk amplification while meeting the original defense criterion.

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。

↑