AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning

TL;DR

AdaBFL introduces a multi-layer adaptive aggregation method to enhance Byzantine robustness in federated learning, effectively countering complex attacks and adapting defense strategies.

Contribution

It proposes a novel three-layer adaptive defense mechanism for federated learning that adjusts to various attack types and provides convergence guarantees.

Findings

AdaBFL outperforms existing methods in robustness across multiple datasets.

The method effectively adapts to complex Byzantine attacks.

Convergence properties are established under non-convex, non-iid data settings.

Abstract

Federated learning (FL) is a popular distributed learning paradigm in machine learning, which enables multiple clients to collaboratively train models under the guidance of a server without exposing private client data. However, FL's decentralized nature makes it vulnerable to poisoning attacks, where malicious clients can submit corrupted models to manipulate the system. To counter such attacks, although various Byzantine-robust methods have been proposed, these methods struggle to provide balanced defense against multiple types of attacks or rely on possessing the dataset in the server. To deal with these drawbacks, thus, we propose an effective multi-layer defensive adaptive aggregation for Bzantine-robust federated learning (AdaBFL) based on a novel three-layer defensive mechanism, which can adaptively adjust the weights of defense algorithms to counter complex attacks. Moreover, we provide convergence properties of our AdaBFL method under the non-convex setting on non-iid data. Comprehensive experiments across multiple datasets validate the superiority of our AdaBFL over the comparable algorithms.