Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference↗ (원문, 새 창)

본문 미리보기

arXiv:2610.27213v1 Announce Type: new 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 us