Work

Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters

Year: 2023

Type: preprint

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 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 $(ε, δ)$-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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2309.05901

Authors: Haney, Samuel, Shoemate, Michael, Tian, Grace, Vadhan, Salil, Vyrros, Andrew, Xu, Vicki, Zhang, Wanrong

Institution: Harvard University

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Alfred P. Sloan Foundation

Award: HNDS-I: Bringing Differential Privacy to Social Science Data Repositories

OpenAlex ID: W4386721687

Cites:

Cited by:

Related to: 10