Byzantine-Resilient Federated Learning via Distributed Optimization
This addresses security vulnerabilities in federated learning systems, offering a more resilient approach against malicious participants, though it appears incremental by adapting existing optimization techniques.
The paper tackled the problem of Byzantine attacks in Federated Learning by proposing distributed optimization as a robust alternative, showing that the Primal-Dual Method of Multipliers achieves higher model utility, faster convergence, and improved stability compared to traditional methods in experiments on datasets like MNIST.
Byzantine attacks present a critical challenge to Federated Learning (FL), where malicious participants can disrupt the training process, degrade model accuracy, and compromise system reliability. Traditional FL frameworks typically rely on aggregation-based protocols for model updates, leaving them vulnerable to sophisticated adversarial strategies. In this paper, we demonstrate that distributed optimization offers a principled and robust alternative to aggregation-centric methods. Specifically, we show that the Primal-Dual Method of Multipliers (PDMM) inherently mitigates Byzantine impacts by leveraging its fault-tolerant consensus mechanism. Through extensive experiments on three datasets (MNIST, FashionMNIST, and Olivetti), under various attack scenarios including bit-flipping and Gaussian noise injection, we validate the superior resilience of distributed optimization protocols. Compared to traditional aggregation-centric approaches, PDMM achieves higher model utility, faster convergence, and improved stability. Our results highlight the effectiveness of distributed optimization in defending against Byzantine threats, paving the way for more secure and resilient federated learning systems.