The Target-Charging Technique for Privacy Accounting across Interactive Computations
Data Structures and Algorithms
2023-04-13 v2
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- selection from private candidates and extends their remarkable privacy enhancement benefits from noisy Lipschitz functions to general private algorithms.
Cite
@article{arxiv.2302.11044,
title = {The Target-Charging Technique for Privacy Accounting across Interactive Computations},
author = {Edith Cohen and Xin Lyu},
journal= {arXiv preprint arXiv:2302.11044},
year = {2023}
}