Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
PROCEEDINGS OF THE 2023 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, CCS 2023(2023)
摘要
In this paper, we study the concurrent composition of interactive mechanisms with adaptively chosen privacy-loss parameters. In this setting, the adversary can interleave queries to existing interactive mechanisms, as well as create new ones. We prove that every valid privacy filter and odometer for noninteractive mechanisms extends to the concurrent composition of interactive mechanisms if privacy loss is measured using (is an element of,delta)-DP, f-DP, or Renyi DP of fixed order. Our results offer strong theoretical foundations for enabling full adaptivity in composing differentially private interactive mechanisms, showing that concurrency does not affect the privacy guarantees. We also provide an implementation for users to deploy in practice.
更多查看译文
关键词
Differential Privacy,Interactive Mechanisms,Concurrent Composition,Adaptivity
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要