arXiv cs.CL· Mingchen Li, Zifan Peng, Kewei Sha, Lavinia F Pieptea, Heng Fan, Junhua Ding, Meikang Qiu, Yunhe Feng·· 12 小时前AI 评分29
Profile-DP：面向个性化 LLM 推理中用户可控档案发布的差分隐私框架
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
AI 导读
Profile-DP 是一个策略感知的本地差分隐私框架，专门用于个性化 LLM 推理中的用户档案发布，可在将公开指令、档案 schema 和已授权事实视为公开侧信息的前提下，对用户未公开事实的释放提供可证明的隐私上界。
正文 · 原文
Abstract:Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests with rich, user-specific facts. This paradigm exposes the user profile itself, together with the user's explicit sharing preferences. We introduce Profile-DP, a policy-aware local differential privacy framework designed specifically for user-profile release in personalized LLM inference. Profile-DP provably bounds the release of user-withheld facts while treating public instructions, profile schemas, and authorized facts as public side information. By generating a privatized profile that composes with the public instruction prior to answer generation, our framework decouples formal privacy guarantees from downstream model behavior. We develop two finite-domain mechanisms satisfying Profile-DP: DP-SLOT independently perturbs protected attributes, while DP-BLOCK uses public semantic decisions to coordinate their release and jointly sample related attributes. A positive, public compatibility prior connects these attributes while preserving a profile-level privacy bound. On PEEP, DP-BLOCK leads the utility composite among DP methods at all 13 structured budgets and is closest to the ideal privacy--utility point in 18 of 26 format--budget settings under our composite weighting. Direct measurements reveal complementary strengths: DP-BLOCK discloses less, while DP-SLOT retains more authorized facts. These results make policy-aware profile release a practical basis for studying privacy and personalization.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.27213 [cs.CR] |
| (or arXiv:2610.27213v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27213 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mingchen Li [view email]
[v1]
Mon, 19 Oct 2026 19:44:02 UTC (370 KB)
来源：arXiv cs.CL · arxiv.org