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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Personalized Wireless Federated Learning for Large Language Models
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their deployment in wireless networks still face challenges, i.e., a lack of privacy and security protection mechanisms. Federa…
Federated LearningPrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation
Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute f…
SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs
Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs…
Federated LearningLUNAR: Benchmarking Personalized Large Language Models on UNiversal User BehAvioR Logs
Existing personalized LLM benchmarks primarily rely on textual personas or isolated behavioral signals, providing limited evaluation of cross-domain behavioral personalization, where responses must be grounded in heterog…
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones,…
Federated LearningPersonalized Federated Learning