Numerical Composition of Differential Privacy

Main Article Content

Sivakanth Gopi
Yin Tat Lee
Lukas Wutschitz

Abstract

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of \emph{privacy loss random variables} to quantify the privacy loss of DP algorithms.
The running time and memory needed for our algorithm to approximate the privacy curve of a DP algorithm composed with itself $k$ times is $\tilde{O}(\sqrt{k})$. This improves over the best prior method by Koskela et al. (2021) which requires $\tilde{\Omega}(k^{1.5})$ running time. We demonstrate the utility of our algorithm by accurately computing the privacy loss of DP-SGD algorithm of Abadi et al. (2016) and showing that our algorithm speeds up the privacy computations by a few orders of magnitude compared to prior work, while maintaining similar accuracy.

Article Details

How to Cite
Gopi, Sivakanth, Yin Tat Lee, and Lukas Wutschitz. 2024. “Numerical Composition of Differential Privacy”. Journal of Privacy and Confidentiality 14 (1). https://doi.org/10.29012/jpc.870.
Section
TPDP 2022

Most read articles by the same author(s)