FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
This addresses the problem of adversarial client behavior in federated learning for privacy-preserving collaborative training, offering a robust solution without assumptions on adversarial fractions, though it is incremental as it builds on existing robust aggregation methods.
The paper tackles Byzantine attacks in federated learning by proposing FedGreed, a loss-based aggregation method that selects clients with minimal loss on a trusted server dataset, and it outperforms standard and robust baselines on datasets like MNIST, FMNIST, and CIFAR-10 in adversarial scenarios.
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.