Metraipolis › archive › dc_5f8b79bee71a
Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy — arXiv:2611.01218
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01218
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:17:10.271Z
- SHA-256 of the archived text
8adb1bdf9bf6ce2cf9e5d1b1fe661df5abae8909f33e9029765f933695f54552- Stable URL of this page
https://metraipolis.com/documento/dc_5f8b79bee71a
How to cite
Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy — arXiv:2611.01218 — arXiv (en), https://arxiv.org/abs/2611.01218 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f8b79bee71a (Metraipolis archive dc_5f8b79bee71a, sha256 8adb1bdf9bf6ce2cf9e5d1b1fe661df5abae8909f33e9029765f933695f54552)
BibTeX
@misc{dc5f8b79bee71a,
title = {Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy — arXiv:2611.01218},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01218},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f8b79bee71a; sha256 8adb1bdf9bf6ce2cf9e5d1b1fe661df5abae8909f33e9029765f933695f54552},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01218. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds in various estimation problems. Moreover, it is known that a mechanism satisfying $\mu$-GDP satisfies $(\mu^2/2)$-zCDP, whereas the converse fails to hold at the same calibration. In this paper, we establish the optimal reverse conversion, showing that every $\rho$-zCDP mechanism satisfies $\mu_{\mathrm{zCDP}}(\rho)$-GDP, where $\mu_{\mathrm{zCDP}}(\rho)=2\Phi^{-1}((1+e^{-t_\rho})^{-1})$ and $t_\rho$ uniquely solves the equation $\rho=t_\rho\tanh(t_\rho/2)$. We also obtain simplified bounds $\sqrt{\pi\rho}\leq\mu_{\mathrm{zCDP}}(\rho)\leq\sqrt{8\rho}$, with sharp constants, which imply equivalence of the two frameworks up to constants. This explains why their minimax risks agree up to a constant rescaling of the privacy budget. We show that the squared conversion is strictly convex, which implies that converting zCDP to GDP before applying composition or group privacy yields a tighter GDP guarantee than converting afterward. We also derive the sharp conversion from bounded-range and logistic DP mechanisms (e.g., exponential mechanism) to GDP, where converting before composition but after group privacy gives the tighter guarantee.
Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2611.01218 — 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 2026-11-03T11:02:07.201Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).