Concurrent Composition Theorems for Differential Privacy
Salil P. Vadhan, Wanrong Zhang
Abstract
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 ( , 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 [Lyu22] proves a similar result to ours for ( , δ)-DP, as well as a concurrent composition theorem for Rényi DP. We also provide a simple proof of Lyu's concurrent composition theorem for Rényi DP. Lyu leaves the general case of f -DP as an open problem, which we solve in this paper.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 0f47e254-22db-4210-9cc7-356571b55c67Cited by top-tier papers7
- Composition Theorems for Interactive Differential PrivacyXin LyuNeurIPS 2022 · 29 citations
- Faster Differentially Private Convex Optimization via Second-Order MethodsArun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Guha ThakurtaNeurIPS 2023 · 18 citations
- Adaptive Privacy Composition for Accuracy-first MechanismsRyan M. Rogers, Gennady Samorodnitsky, Zhiwei Steven Wu, Aaditya RamdasNeurIPS 2023 · 6 citations
- Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss ParametersSamuel Haney, Michael Shoemate, Grace Tian, Salil P. Vadhan et al.CCS 2023 · 4 citations
- Private Learning of Littlestone Classes, RevisitedXin LyuSTOC 2026 · 4 citations
Builds on1
Related papers
- Log-Concave and Multivariate Canonical Noise Distributions for Differential PrivacyJordan Awan, Jinshuo DongNeurIPS 2022 · 13 citations
- Two Views of Constrained Differential Privacy: Belief Revision and UpdateLikang Liu, Keke Sun, Chunlai Zhou, Yuan FengAAAI 2023 · 5 citations
- General-Purpose f-DP Estimation and Auditing in a Black-Box SettingÖnder Askin, Holger Dette, Martin Dunsche, Tim Kutta et al.USENIX Security 2025
- Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential PrivacyBogdan Kulynych, Juan Felipe Gómez, Georgios Kaissis, Jamie Hayes et al.NeurIPS 2025 · 15 citations
- On the Rényi Differential Privacy of the Shuffle ModelAntonious M. Girgis, Deepesh Data, Suhas N. Diggavi, Ananda Theertha Suresh et al.CCS 2021 · 1 citation
