Realisation-level privacy filtering

Conference item

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 realisationlevel 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 (ϵ, δ)-differential privacy, with ϵ and δ chosen by the data handler. Through numerical evidence, we demonstrate that realisation-level filtering provides a complementary 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.

Authors: Taylor, S; Vippathalla, P; Coon, JP

• Publication status: Accepted
• Peer review status: Peer reviewed
• Publisher: IEEE
• Acceptance date: 2026-03-28
• Event title: IEEE International Symposium on Information Theory (ISIT2026)
• Event location: Guangzhou, China
• Event website: https://2026.ieee-isit.org/
• Event start date: 2026-06-28
• Event end date: 2026-07-03
• Language: English