The Target-Charging Technique for Privacy Analysis across Interactive Computations

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Differential Privacy; Adaptive Composition; Sparse Vector Technique
TL;DR: We propose a privacy analysis method that significantly generalizes the applicability of the Sparse Vector Technique (SVT)
Abstract: We propose the \emph{Target Charging Technique} (TCT), a unified privacy analysis framework for interactive settings where a sensitive dataset is accessed multiple times using differentially private algorithms. Unlike traditional composition, where privacy guarantees deteriorate quickly with the number of accesses, TCT allows computations that don't hit a specified \emph{target}, often the vast majority, to be essentially free (while incurring instead a small overhead on those that do hit their targets). TCT generalizes tools such as the sparse vector technique and top-k selection from private candidates and extends their remarkable privacy enhancement benefits from noisy Lipschitz functions to general private algorithms.
Supplementary Material: pdf
Submission Number: 1669