Grace Tian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Grace Tian has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Vyrros
Harvard University, Cambridge, MA, USA
1 shared publication - Michael Shoemate
Harvard University, Cambridge, Massachusetts, USA
1 shared publication - Salil Vadhan
Harvard University, Cambridge, USA
1 shared publication - Samuel Haney
Duke University
1 shared publication - Vicki Xu
Harvard University, Cambridge, MA, USA
1 shared publication - Wanrong Zhang
Harvard University, Cambridge, MA, USA
1 shared publication
Latest Publications
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1949-1963
Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
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, ƒ-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.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1949-1963
Open AccessConcurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
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, ƒ-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.