EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning

TL;DR

EBS-CFL introduces a secure, efficient, and Byzantine-robust clustered federated learning scheme that preserves user privacy, detects malicious attacks, and improves training performance in heterogeneous data environments.

Contribution

It proposes a novel EBS-CFL scheme that maintains cluster privacy, detects poisoning attacks, and enhances efficiency compared to existing methods.

Findings

Supports effective CFL training with privacy preservation.

Detects poisonous attacks without exposing individual gradients.

Achieves higher efficiency, especially when the number of clusters is one.

Abstract

Despite federated learning (FL)'s potential in collaborative learning, its performance has deteriorated due to the data heterogeneity of distributed users. Recently, clustered federated learning (CFL) has emerged to address this challenge by partitioning users into clusters according to their similarity. However, CFL faces difficulties in training when users are unwilling to share their cluster identities due to privacy concerns. To address these issues, we present an innovative Efficient and Robust Secure Aggregation scheme for CFL, dubbed EBS-CFL. The proposed EBS-CFL supports effectively training CFL while maintaining users' cluster identity confidentially. Moreover, it detects potential poisonous attacks without compromising individual client gradients by discarding negatively correlated gradients and aggregating positively correlated ones using a weighted approach. The server also authenticates correct gradient encoding by clients. EBS-CFL has high efficiency with client-side overhead O(ml + m^2) for communication and O(m^2l) for computation, where m is the number of cluster identities, and l is the gradient size. When m = 1, EBS-CFL's computational efficiency of client is at least O(log n) times better than comparison schemes, where n is the number of clients.In addition, we validate the scheme through extensive experiments. Finally, we theoretically prove the scheme's security.