LGCRSTMEMLOct 22, 2025

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

arXiv:2510.19934v14 citationsh-index: 13
Originality Incremental advance
AI Analysis

This work addresses privacy-utility trade-offs for users in decentralized federated learning systems, representing an incremental improvement in privacy accounting methods.

The paper tackled the challenge of accurately quantifying privacy budgets in decentralized federated learning by developing two new accounting methods within the $f$-differential privacy framework, resulting in tighter privacy bounds and improved utility compared to existing approaches.

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 $(ε,δ)$ bounds and improved utility compared to Rényi DP-based approaches, illustrating the benefits of $f$-DP in decentralized privacy accounting.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes