HOME / PUBLICATIONS /

Concurrent composition for interactive differential privacy with adaptive privacy-loss parameters

Citation:

Haney, Samuel, Michael Shoemate, Grace Tian, Salil P. Vadhan, Andrew Vyrros, Vicki Xu, and Wanrong Zhang. “Concurrent composition for interactive differential privacy with adaptive privacy-loss parameters.” Weizhi Meng, Christian Damsgaard Jensen, Cas Cremers, and Engin Kirda, eds., Proceedings of the 30th ACM SIGAC Conference on Computer and Communications Security (CCS '23). ACM, 2023.
CCS 2023.pdf683 KB

Abstract:

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 interac tive 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 (ε, δ)-DP, f -DP, or Rényi 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.

 

 

History: Received a CCS '23 Distinguished Paper Award. Preliminary version presented as a poster at TPDP '23 and posted as: https://arxiv.org/abs/2309.05901.

Publisher's Version