这项研究提出了个性化隐私控制的新方法，通过注意力头干预在LLMs中实现，对于关注隐私保护的用户来说是个好消息，它比现有方法更可靠地保护用户隐私。
随着代理式AI的兴起，LLMs能够访问多样化的用户数据，引发了隐私问题。本研究引入个性化隐私概念，结合用户特定的披露偏好进行隐私控制。提出P3Bench基准，扩展上下文隐私策略。实验表明，基于提示的策略无法可靠地执行个性化隐私策略，Qwen2.5-7B和Gemma3-4B的平均策略无知率分别为51.25%和74.28%。针对此问题，提出Repair方法，通过调整披露行为以符合策略响应，显著提高对用户特定隐私偏好的遵守率。
Personalized Privacy Control in LLMs via Attention Head Intervention
The rise of agentic AI enables LLMs to access diverse user data, raising critical privacy concerns. Prior work on contextual privacy studies whether LLMs regulate information disclosure according to context-dependent norms. However, acceptable disclosure boundaries may vary across users even within the same context. To address this limitation, we introduce \textit{personalized privacy}, which incorporates user-specific disclosure preferences into privacy control. We further present P3Bench~(\textbf{P}ersonalized \textbf{P}rivacy \textbf{P}reservation \textbf{Bench}mark), a novel benchmark extending contextual privacy policies with personalized disclosure policies. Experiments show that prompt-based policies fail to reliably enforce personalized privacy policies, with Qwen2.5-7B and Gemma3-4B showing average policy ignorance ratios of 51.25\% and 74.28\%, respectively. Finally, to address this problem, we propose \textsc{Repair}, a robust inference-time attention head intervention method that adjusts disclosure behavior toward policy-consistent responses. Our method significantly improves adherence to user-specific privacy preferences by reducing cases where the model fails to follow the given policy.