Tackling Selfish Clients in Federated Learning

TL;DR

This paper introduces RFL-Self, a robust aggregation method in federated learning that estimates and mitigates the impact of selfish clients, maintaining model accuracy even with malicious participants.

Contribution

The paper proposes a novel robust aggregation strategy using median-based estimation to counteract selfish clients in federated learning.

Findings

RFL-Self effectively mitigates the impact of 2% selfish clients.

Selfish clients can reduce accuracy by up to 36%.

RFL-Self maintains model performance without degradation.

Abstract

Federated Learning (FL) is a distributed machine learning paradigm facilitating participants to collaboratively train a model without revealing their local data. However, when FL is deployed into the wild, some intelligent clients can deliberately deviate from the standard training process to make the global model inclined toward their local model, thereby prioritizing their local data distribution. We refer to this novel category of misbehaving clients as selfish. In this paper, we propose a Robust aggregation strategy for FL server to mitigate the effect of Selfishness (in short RFL-Self). RFL-Self incorporates an innovative method to recover (or estimate) the true updates of selfish clients from the received ones, leveraging robust statistics (median of norms) of the updates at every round. By including the recovered updates in aggregation, our strategy offers strong robustness against selfishness. Our experimental results, obtained on MNIST and CIFAR-10 datasets, demonstrate that just 2% of clients behaving selfishly can decrease the accuracy by up to 36%, and RFL-Self can mitigate that effect without degrading the global model performance.