Fully Adaptive Composition for Gaussian Differential Privacy

TL;DR

This paper demonstrates that Gaussian Differential Privacy (GDP) maintains its composability even under fully adaptive analysis, allowing for flexible privacy-preserving data analysis without loss of privacy guarantees.

Contribution

It establishes that GDP composes gracefully in adaptive settings, matching nonadaptive composition parameters, which was previously unknown.

Findings

GDP composes gracefully in adaptive scenarios

Adaptive analysts can select mechanisms based on previous answers without privacy loss

GDP's composition parameters remain unchanged in adaptive settings

Abstract

We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst. Such an analyst selects mechanisms (to be run on a sensitive data set) and their privacy budgets adaptively, that is, based on the answers from other mechanisms run previously on the same data set. In the language of Rogers, Roth, Ullman and Vadhan, this gives a filter for GDP with the same parameters as for nonadaptive composition.