Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy

Published: 21 Sept 2023, Last Modified: 14 Jan 2024NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Differential privacy, federated data analytics, discrete valued-mechanism, distributed mean estimation
TL;DR: Analyze the $f$-differential privacy guarantees for discrete-valued mechanisms and propose a new differentially privacy compressor
Abstract: We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. The commonly adopted compression schemes introduce information loss into local data while improving communication efficiency, and it remains an open problem whether such discrete-valued mechanisms provide any privacy protection. In this paper, we study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP). More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms, including the binomial noise and the binomial mechanisms that are proposed for privacy preservation, and the sign-based methods that are proposed for data compression, in closed-form expressions. We further investigate the amplification in privacy by sparsification and propose a ternary stochastic compressor. By leveraging compression for privacy amplification, we improve the existing methods by removing the dependency of accuracy (in terms of mean square error) on communication cost in the popular use case of distributed mean estimation, therefore breaking the three-way tradeoff between privacy, communication, and accuracy.
Supplementary Material: zip
Submission Number: 4901