FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk
This addresses fairness in privacy for federated learning systems, particularly in human-centric applications, representing an incremental advance by combining server-side and client-side strategies.
The paper tackles disparities in privacy risk in federated learning by introducing FinP, a framework that reduces vulnerability to source inference attacks, achieving a 57.14% improvement in fairness on CIFAR-10 compared to state-of-the-art methods with minimal utility loss.
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.