Realisation-Level Privacy Filtering

Computer Science > Cryptography and Security [Submitted on 9 Apr 2026] Realisation-Level Privacy Filtering Sophie Taylor, Praneeth Vippathalla, Justin Coon We study differentially private data release, where a database is accessed through successive, possibly adaptive queries and mechanisms. Existing composition theorems and privacy filters combine worst case per-round privacy parameters, leaving room for more refined accounting based on realised leakage, which we term realisation-level accounting. We propose a realisation-level filtering approach to determine stopping times for data releases, and design one such filter. Despite technical challenges arising from conditioning on realisations and stopping time, we prove that the filter guarantees (\epsilon, \delta)-differential privacy, with \epsilon and \delta chosen by the data handler. Through numerical evidence, we demonstrate that realisation-level filtering provides a path to better utility beyond mechanism-level methods. Furthermore, our proposed filter applies to arbitrary mechanisms, including those that are badly behaved under Rényi differential privacy. Subjects: Cryptography and Security (cs.CR); Information Theory (cs.IT) Cite as: arXiv:2604.08630 [cs.CR]   (or arXiv:2604.08630v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.08630 Focus to learn more Submission history From: Sophie Taylor [view email] [v1] Thu, 9 Apr 2026 16:31:38 UTC (187 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.IT math math.IT References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)