Newest papers

Formalization of Rényi Differential Privacy in Isabelle/HOL (Draft version)

Tetsuya Sato · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25636 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Дифференциальная конфиденциальность (DP) - это золотое определение конфиденциальности, предназначенное для оценки гарантии конфиденциальности баз данных. Дифференциальная конфиденциальность Rényi (RDP) является важным вариантом DP, который дает жесткие оценки алгоритмов машинного обучения. Эти формулировки легко понять, но оценка конфиденциальности для реальных баз данных является сложной. Даже небольшое изменение в базе данных может нарушить ее конфиденциальность, и оценки DP и RDP самих сложны. В частности, оценки RDP в недавних исследованиях стали намного сложнее. Поэтому формальная проверка их изучалась более десятилетия. В этой статье мы предлагаем библиотеку Isabelle/HOL для формализации дифференциальной конфиденциальности Rényi в

Machine translation (Meta M2M100); the English original follows.

Abstract

Differential privacy (DP) is a gold-standard definition of privacy designed to evaluate the privacy guarantee of databases. Rényi differential privacy (RDP) is an important variant of DP that gives tight evaluations of machine learning algorithms. These formulations are easy to understand, but evaluating privacy for actual databases is complicated. Even a small change in the database can break its privacy, and evaluations of DP and RDP themselves are complicated. In particular, RDP evaluations in recent studies have become much harder. Therefore, formal verification of them has been studied for over a decade. In this paper, we propose an Isabelle/HOL library for formalizing Rényi differential privacy in a general setting. We first formalize RDP for continuous distributions. As a technical basis, we formalize several properties of convex functions and $f$-divergences for nonnegative convex functions. We formalize basic properties of RDP, conversion laws from RDP to DP, the moment accountants in DP, and the Gaussian mechanism and its RDP. Finally, we discuss the stochastic gradient descent mechanism with Gaussian noise and formalize a rough evaluation of its RDP and DP.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Differential privacy, Computer science, Regular polygon, Gaussian, Information privacy, Differential (mechanical device)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25636, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange