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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Zhiqiang, Bao, Haiyong, Guan, Menghong, Pan, Hao, Huang, Cheng, Dai, Hong-Ning
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908408999837696
author Li, Zhiqiang
Bao, Haiyong
Guan, Menghong
Pan, Hao
Huang, Cheng
Dai, Hong-Ning
author_facet Li, Zhiqiang
Bao, Haiyong
Guan, Menghong
Pan, Hao
Huang, Cheng
Dai, Hong-Ning
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning
Li, Zhiqiang
Bao, Haiyong
Guan, Menghong
Pan, Hao
Huang, Cheng
Dai, Hong-Ning
Cryptography and Security
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
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.
title EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning
topic Cryptography and Security
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2506.13612