Metraipolis › archive › dc_e3ff508392a2

Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference — arXiv:2610.27213

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27213
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:33.222Z
SHA-256 of the archived text
64a9d33d96d275fcc52b22bcade5932c1d85c341d9f471062de5442a226f2c78
Stable URL of this page
https://metraipolis.com/documento/dc_e3ff508392a2

How to cite

Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference — arXiv:2610.27213 — arXiv (en), https://arxiv.org/abs/2610.27213 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3ff508392a2 (Metraipolis archive dc_e3ff508392a2, sha256 64a9d33d96d275fcc52b22bcade5932c1d85c341d9f471062de5442a226f2c78)
BibTeX
@misc{dce3ff508392a2,
  title = {Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference — arXiv:2610.27213},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27213},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3ff508392a2; sha256 64a9d33d96d275fcc52b22bcade5932c1d85c341d9f471062de5442a226f2c78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27213. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.27213 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-21T07:05:43.537Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).