A Byzantine-Resilient Dual Subgradient Method for Vertical Federated Learning

Kun Yuan; Zhaoxian Wu; Qing Ling

ICASSP 2022accepted0 citations

A Byzantine-Resilient Dual Subgradient Method for Vertical Federated Learning

Abstract

Federated learning (FL) raises new challenges on security risks, especially when the FL system involves Byzantine clients that send corrupted or adversarial messages to the central server for deteriorating the training paradigm. While there is an extensive research on robust algorithms for horizontal or data-partitioned FL problems, the exploration in Byzantine-resilient vertical or feature-partitioned FL is quite limited. In this paper, we provide a problem formulation of vertical FL in the presence of Byzantine attacks, and propose a Byzantine-resilient dual subgradient method. Convergence analysis is established, and the influence of the Byzantine clients is also clarified. Numerical experiments show the proposed algorithm is robust to various Byzantine attacks on vertical FL.

BibTeX

@inproceedings{icassp2022_abyzantineresili,
  title = {A Byzantine-Resilient Dual Subgradient Method for Vertical Federated Learning},
  author = {Kun Yuan and Zhaoxian Wu and Qing Ling},
  booktitle = {ICASSP 2022},
  year = {2022}
}