FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning

TL;DR

FedGreed is a robust aggregation method for federated learning that effectively defends against Byzantine attacks without prior knowledge of the attack fraction, ensuring reliable model training even with heterogeneous data.

Contribution

It introduces FedGreed, a loss-based aggregation strategy that operates under arbitrary adversarial presence and non-IID data, with proven convergence guarantees.

Findings

Outperforms standard and robust baselines in adversarial scenarios

Effective under non-IID data distributions

Demonstrates convergence and bounded optimality gaps

Abstract

Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device. In this work, we address FL settings where clients may behave adversarially, exhibiting Byzantine attacks, while the central server is trusted and equipped with a reference dataset. We propose FedGreed, a resilient aggregation strategy for federated learning that does not require any assumptions about the fraction of adversarial participants. FedGreed orders clients' local model updates based on their loss metrics evaluated against a trusted dataset on the server and greedily selects a subset of clients whose models exhibit the minimal evaluation loss. Unlike many existing approaches, our method is designed to operate reliably under heterogeneous (non-IID) data distributions, which are prevalent in real-world deployments. FedGreed exhibits convergence guarantees and bounded optimality gaps under strong adversarial behavior. Experimental evaluations on MNIST, FMNIST, and CIFAR-10 demonstrate that our method significantly outperforms standard and robust federated learning baselines, such as Mean, Trimmed Mean, Median, Krum, and Multi-Krum, in the majority of adversarial scenarios considered, including label flipping and Gaussian noise injection attacks. All experiments were conducted using the Flower federated learning framework.