Coordinate-Wise Median in Byzantine Federated Learning

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

Proceedings of the International Workshop on Secure and Efficient Federated Learning in conjunction with ACM AsiaCCS 2025, FL-AsiaCCS 2025

Abstract

Federated learning enables clients to train local models on private data while exchanging model updates only. A key step in this process is gradient aggregation. We investigate the coordinate-wise median as an aggregation rule in both centralized and decentralized federated learning under Byzantine failures. In order to lower the communication cost in the decentralized setting, we allow clients to agree approximately on model parameters, which is referred to as approximate agreement problem. We propose two aggregation algorithms for centralized coordinate-wise median aggregation: the Minimum Diameter (MD) algorithm and the Hyperbox algorithm. We prove that both satisfy the box validity condition and can tolerate up to n/3 and n/2 Byzantine clients, respectively. We further show that only the Hyperbox algorithm can be generalized to the decentralized setting. Through empirical evaluation, we demonstrate that the MD algorithm with coordinate-wise median aggregation is more resilient to sign-flip attacks than its mean-based counterpart, highlighting the robustness of median-based aggregation in adversarial environments.

Description

Publisher Copyright: © 2025 Copyright held by the owner/author(s)

Other note

Citation

Cambus, M, Melnyk, D, Milentijevic, T & Schmid, S 2025, Coordinate-Wise Median in Byzantine Federated Learning. in Proceedings of the International Workshop on Secure and Efficient Federated Learning in conjunction with ACM AsiaCCS 2025, FL-AsiaCCS 2025., 5, ACM, International Workshop on Secure and Efficient Federated Learning, Hanoi, Viet Nam, 26/08/2025. https://doi.org/10.1145/3709023.3737691