Concurrent Composition Theorems for Differential Privacy

07/18/2022
by   Salil Vadhan, et al.
0

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 <cit.> proves a similar result to ours for (,δ)-DP, as well as a concurrent composition theorem Rènyi DP (which we also claimed in an earlier version of this paper, but with an incorrect proof). Lyu leaves the general case of f-DP as an open problem, which we solve in this paper.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2022

Composition Theorems for Interactive Differential Privacy

An interactive mechanism is an algorithm that stores a data set and answ...
research
09/12/2023

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

In this paper, we study the concurrent composition of interactive mechan...
research
10/18/2021

Flexible Accuracy for Differential Privacy

Differential Privacy (DP) has become a gold standard in privacy-preservi...
research
02/27/2023

On Differentially Private Online Predictions

In this work we introduce an interactive variant of joint differential p...
research
05/11/2021

On the Renyi Differential Privacy of the Shuffle Model

The central question studied in this paper is Renyi Differential Privacy...
research
03/02/2021

Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning

Differential Privacy (DP) is the leading approach to privacy preserving ...
research
02/03/2020

Differentially Private k-Means Clustering with Guaranteed Convergence

Iterative clustering algorithms help us to learn the insights behind the...

Please sign up or login with your details

Forgot password? Click here to reset