Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy

TL;DR

This paper introduces new $f$-DP-based privacy accounting methods for decentralized federated learning, providing tighter privacy bounds and better utility by capturing complex communication and local update effects.

Contribution

It develops two novel $f$-DP accounting techniques tailored for decentralized FL, addressing privacy amplification and correlated noise in such settings.

Findings

Tighter $(psilon,elta)$ privacy bounds achieved.

Improved utility over Re9nyi DP-based methods.

Effective privacy accounting in decentralized communication scenarios.

Abstract

Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging due to the co-existence of complex algorithmic components such as decentralized communication and local updates. This paper addresses privacy accounting for two decentralized FL algorithms within the $f$-differential privacy ($f$-DP) framework. We develop two new $f$-DP-based accounting methods tailored to decentralized settings: Pairwise Network $f$-DP (PN-$f$-DP), which quantifies privacy leakage between user pairs under random-walk communication, and Secret-based $f$-Local DP (Sec-$f$-LDP), which supports structured noise injection via shared secrets. By combining tools from $f$-DP theory and Markov chain concentration, our accounting framework captures privacy amplification arising from sparse communication, local iterations, and correlated noise. Experiments on synthetic and real datasets demonstrate that our methods yield consistently tighter $(\epsilon,\delta)$ bounds and improved utility compared to R\'enyi DP-based approaches, illustrating the benefits of $f$-DP in decentralized privacy accounting.