TrustBandit: Optimizing Client Selection for Robust Federated Learning Against Poisoning Attacks

Federated learning enables collaborative model training with privacy preservation. In this framework, individual clients locally train and send updates to a central server for aggregation, making the systems susceptible to poisoning attacks due to the lack of central server visibility. Existing client selection (CS) techniques enhance global accuracy but lack robustness, especially with non-Independently and Identically Distributed (non-IID) data patterns. To address this, our study fortifies CS, emphasizing federated learning's resilience. Specifically, to enhance robustness against poisoning attacks, we integrate a reputation system with Adversarial Multi-Armed Bandit (MAB) algorithms for improved model aggregation. Framing the CS problem as an adversarial MAB problem, our approach effectively estimates each client's reputation, mitigating uncertainties in current reputation values. It establishes a regret bound, showcasing sublinear regret, a desirable characteristic in online learning algorithms. Through experiments on a publicly available dataset, our approach achieves an impressive 94.2% success rate in identifying trustworthy clients.