FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

TL;DR

FinP is a novel framework that enhances fairness in privacy distribution across clients in federated learning by reducing privacy risk disparities and improving robustness against source inference attacks, with minimal utility loss.

Contribution

FinP introduces a dual strategy of adaptive aggregation and client-side regularization to address privacy fairness disparities in federated learning.

Findings

Improves fairness-in-privacy on HAR and CIFAR-10 datasets.

Reduces privacy risk disparities by over 57% on CIFAR-10.

Mitigates source inference attack risks significantly.

Abstract

Ensuring fairness in machine learning extends to the critical dimension of privacy, particularly in human-centric federated learning (FL) settings where decentralized data necessitates an equitable distribution of privacy risk across clients. This paper introduces FinP, a novel framework specifically designed to address disparities in privacy risk by mitigating disproportionate vulnerability to source inference attacks (SIA). FinP employs a two-pronged strategy: (1) server-side adaptive aggregation, which dynamically adjusts client contributions to the global model to foster fairness, and (2) client-side regularization, which enhances the privacy robustness of individual clients. This comprehensive approach directly tackles both the symptoms and underlying causes of privacy unfairness in FL. Extensive evaluations on the Human Activity Recognition (HAR) and CIFAR-10 datasets demonstrate FinP's effectiveness, achieving improvement in fairness-in-privacy on HAR and CIFAR-10 with minimal impact on utility. FinP improved group fairness with respect to disparity in privacy risk using equal opportunity in CIFAR-10 by 57.14% compared to the state-of-the-art. Furthermore, FinP significantly mitigates SIA risks on CIFAR-10, underscoring its potential to establish fairness in privacy within FL systems without compromising utility.