Metraipolis › archive › dc_190c792575b3

Task-aware Kernel Stein certificates for Rényi differential privacy — arXiv:2610.23798

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23798
License (as archived)
CC0-1.0
Archived
2026-10-19T08:46:43.933Z
SHA-256 of the archived text
7101901ab57664c0230de4f9acb31c771a32b8a1f9ca679b3d2aed5b3a11d345
Stable URL of this page
https://metraipolis.com/documento/dc_190c792575b3

How to cite

Task-aware Kernel Stein certificates for Rényi differential privacy — arXiv:2610.23798 — arXiv (en), https://arxiv.org/abs/2610.23798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_190c792575b3 (Metraipolis archive dc_190c792575b3, sha256 7101901ab57664c0230de4f9acb31c771a32b8a1f9ca679b3d2aed5b3a11d345)
BibTeX
@misc{dc190c792575b3,
  title = {Task-aware Kernel Stein certificates for Rényi differential privacy — arXiv:2610.23798},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23798},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_190c792575b3; sha256 7101901ab57664c0230de4f9acb31c771a32b8a1f9ca679b3d2aed5b3a11d345},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can be difficult to compute. In particular, Rènyi differential privacy guarantees that exploit task-specific information, as in Rènyi Pufferfish privacy, can be challenging. Here we use kernel Stein discrepancies based on escort distributions to provide certificates for Rènyi differential privacy. By designing the kernel to focus on the relevant privacy directions, we also derive task-aware privacy certificates. We provide exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms, with separate task-aware guarantees. A real data set example illustrates how the protected comparison set and the released subspace jointly determine the resulting certificates.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.23798 — 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 2026-10-19T08:41:54.798Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).