Tetsuya Sato · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.25636 · cited by 0 works (OpenAlex) · open-access PDF
Rényi 차별 개인 정보 보호 (RDP)는 기계 학습 알고리즘에 대한 엄격한 평가를 제공하는 DP의 중요한 변형입니다. 이러한 형식은 이해하기 쉽지만 실제 데이터베이스에 대한 개인 정보 보호를 평가하는 것은 복잡합니다. 데이터베이스의 소규모 변경조차도 개인 정보 보호를 파괴 할 수 있으며 DP와 RDP 자체의 평가는 복잡합니다. 특히 최근 연구에서 RDP 평가는 훨씬 더 어려워졌습니다. 따라서 10 년 이상 연구되었습니다. 이 논문에서 우리는 Rényi 차별 개인 정보 보호를 일반적인 환경에서 공식화하기 위해 Isabelle / HOL 라이브러리를 제안합니다. 우리는 RDP를 지속적인 분배를위한 RDP를 공식화합니다. 특히 최근 연구에서 RDP 평가는 훨씬 더 어려워졌습니다. 따라서 부드러운 기능의 몇 가지 특성을
Machine translation (Meta M2M100); the English original follows.
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)
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange