Concurrent Composition Theorems for Differential Privacy
Not on the map. Why?
Abstract (arXiv)
We study the concurrent composition properties of interactive differentially private mechanisms, whereby an adversary can arbitrarily interleave its queries to the different mechanisms. We prove that all composition theorems for non-interactive differentially private mechanisms extend to the concurrent composition of interactive differentially private mechanisms, whenever differential privacy is measured using the hypothesis testing framework of f-DP, which captures standard (eps,δ)-DP as a special case. We prove the concurrent composition theorem by showing that every interactive f-DP mechanism can be simulated by interactive post-processing of a non-interactive f-DP mechanism. In concurrent and independent work, Lyu~citelyu2022composition proves a similar result to ours for (eps,δ)-DP, as well as a concurrent composition theorem for R'enyi DP. We also provide a simple proof of Lyu's concurrent composition theorem for R'enyi DP. Lyu leaves the general case of f-DP as an open problem, which we solve in this paper.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jul 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 3; 2026: 2.
8 papers.
- 2022Composition of Differential Privacy & Privacy Amplification by Subsamplingcited by 45
- 2025Privacy amplification by random allocationcited by 15
- 2023Faster Differentially Private Convex Optimization via Second-Order Methodscited by 13
- 2025Private Learning of Littlestone Classes, Revisitedcited by 3
- 2023Adaptive Privacy Composition for Accuracy-first Mechanismscited by 2
- 2025Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditingcited by 1
- 2026Privately Learning Decision Lists and a Differentially Private Winnowcited by 1
- 2026Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipecited by 0
- 2026Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe8 Jul 2026
- 2026Privately Learning Decision Lists and a Differentially Private Winnow7 Feb 2026
- 2025Private Learning of Littlestone Classes, Revisited30 Sep 2025
- 2025Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditing10 Sep 2025
- 2025Privacy amplification by random allocation12 Feb 2025
- 2023Adaptive Privacy Composition for Accuracy-first Mechanisms24 Jun 2023
- 2023Faster Differentially Private Convex Optimization via Second-Order Methods22 May 2023
- 2022Composition of Differential Privacy & Privacy Amplification by Subsampling2 Oct 2022