Failure-tolerant Distributed Learning for Anomaly Detection in Wireless Networks

TL;DR

This paper introduces Tol-FL, a failure-tolerant distributed learning method combining flat- and star-topologies, significantly improving anomaly detection robustness and performance in wireless networks while reducing communication costs.

Contribution

The paper proposes Tol-FL, a novel hybrid topology approach that enhances failure tolerance and detection accuracy in distributed wireless network anomaly detection.

Findings

Outperforms prior methods by up to 8% in AUROC

Effective under client and server failure scenarios

Reduces communication costs compared to existing techniques

Abstract

The analysis of distributed techniques is often focused upon their efficiency, without considering their robustness (or lack thereof). Such a consideration is particularly important when devices or central servers can fail, which can potentially cripple distributed systems. When such failures arise in wireless communications networks, important services that they use/provide (like anomaly detection) can be left inoperable and can result in a cascade of security problems. In this paper, we present a novel method to address these risks by combining both flat- and star-topologies, combining the performance and reliability benefits of both. We refer to this method as "Tol-FL", due to its increased failure-tolerance as compared to the technique of Federated Learning. Our approach both limits device failure risks while outperforming prior methods by up to 8% in terms of anomaly detection AUROC in a range of realistic settings that consider client as well as server failure, all while reducing communication costs. This performance demonstrates that Tol-FL is a highly suitable method for distributed model training for anomaly detection, especially in the domain of wireless networks.