Metraipolis › archive › dc_09d8c9fc7d4e
Unifying Privacy Accounting: Information Equivalence and Information Loss — arXiv:2610.02414
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02414
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:06:18.510Z
- SHA-256 of the archived text
6a89fc3e4646a0cf8abee1249ccb63dfce76741844247a65c73b59fe5f90d115- Stable URL of this page
https://metraipolis.com/documento/dc_09d8c9fc7d4e
How to cite
Unifying Privacy Accounting: Information Equivalence and Information Loss — arXiv:2610.02414 — arXiv, https://arxiv.org/abs/2610.02414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09d8c9fc7d4e (Metraipolis archive dc_09d8c9fc7d4e, sha256 6a89fc3e4646a0cf8abee1249ccb63dfce76741844247a65c73b59fe5f90d115)
BibTeX
@misc{dc09d8c9fc7d4e,
title = {Unifying Privacy Accounting: Information Equivalence and Information Loss — arXiv:2610.02414},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02414},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09d8c9fc7d4e; sha256 6a89fc3e4646a0cf8abee1249ccb63dfce76741844247a65c73b59fe5f90d115},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Differential privacy (DP) admits several notions, but the choice among them may affect both privacy analysis and utility. In this paper, we consider four mainstream curve-based privacy notions within a unified information-theoretic framework. For a fixed ordered pair of output distributions, we establish information equivalence among the two directional privacy profiles of $(\varepsilon,\delta)$-DP, the pair of hypothesis-testing trade-off functions, and the extended privacy-loss distribution. The exact Rényi differential privacy (RDP) curve joins this equivalence class whenever it is finite at some order greater than one. Under this mild condition, choosing among these notions changes only their semantic interpretation and computational requirements. In contrast, taking the maximum of the directional privacy profiles or compressing the RDP curve into a single zero-concentrated differential privacy (zCDP) parameter can lose information. We quantify the information loss between the exact RDP curve and its zCDP bound for standard noise mechanisms. This gap is zero for Gaussian noise but generally positive for Gaussian-mixture, Laplace, discrete Gaussian, and Poisson-subsampled Gaussian mechanisms. Moreover, this gap grows linearly with the number of independently composed mechanisms. Our information-theoretic perspective has practical consequences. At the same certified privacy level, retaining the full RDP curve rather than using zCDP reduces the required noise variance by up to $45\%$ for Gaussian-mixture noise in workloads comparable in size to the American Community Survey. For DP-SGD on Fashion-MNIST under Poisson subsampling, an RDP-based privacy accountant improves test accuracy by up to $8.73$ percentage points compared to a zCDP-based accountant when both are calibrated to the same $(\varepsilon,\delta)$ guarantee. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Information Theory (cs.IT); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2610.02414 — 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 2026-10-05T23:01:08.531Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).