Understanding Byzantine Robustness in Federated Learning with A Black-box Server

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Fangyuan, Xie, Yuexiang, Ren, Xuebin, Ding, Bolin, Yang, Shusen, Li, Yaliang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916353418461184
author Zhao, Fangyuan
Xie, Yuexiang
Ren, Xuebin
Ding, Bolin
Yang, Shusen
Li, Yaliang
author_facet Zhao, Fangyuan
Xie, Yuexiang
Ren, Xuebin
Ding, Bolin
Yang, Shusen
Li, Yaliang
contents Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates. Previous works propose to apply robust rules to aggregate updates from participators against different types of Byzantine attacks, while at the same time, attackers can further design advanced Byzantine attack algorithms targeting specific aggregation rule when it is known. In practice, FL systems can involve a black-box server that makes the adopted aggregation rule inaccessible to participants, which can naturally defend or weaken some Byzantine attacks. In this paper, we provide an in-depth understanding on the Byzantine robustness of the FL system with a black-box server. Our investigation demonstrates the improved Byzantine robustness of a black-box server employing a dynamic defense strategy. We provide both empirical evidence and theoretical analysis to reveal that the black-box server can mitigate the worst-case attack impact from a maximum level to an expectation level, which is attributed to the inherent inaccessibility and randomness offered by a black-box server.The source code is available at https://github.com/alibaba/FederatedScope/tree/Byzantine_attack_defense to promote further research in the community.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06042
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding Byzantine Robustness in Federated Learning with A Black-box Server
Zhao, Fangyuan
Xie, Yuexiang
Ren, Xuebin
Ding, Bolin
Yang, Shusen
Li, Yaliang
Cryptography and Security
Artificial Intelligence
Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates. Previous works propose to apply robust rules to aggregate updates from participators against different types of Byzantine attacks, while at the same time, attackers can further design advanced Byzantine attack algorithms targeting specific aggregation rule when it is known. In practice, FL systems can involve a black-box server that makes the adopted aggregation rule inaccessible to participants, which can naturally defend or weaken some Byzantine attacks. In this paper, we provide an in-depth understanding on the Byzantine robustness of the FL system with a black-box server. Our investigation demonstrates the improved Byzantine robustness of a black-box server employing a dynamic defense strategy. We provide both empirical evidence and theoretical analysis to reveal that the black-box server can mitigate the worst-case attack impact from a maximum level to an expectation level, which is attributed to the inherent inaccessibility and randomness offered by a black-box server.The source code is available at https://github.com/alibaba/FederatedScope/tree/Byzantine_attack_defense to promote further research in the community.
title Understanding Byzantine Robustness in Federated Learning with A Black-box Server
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2408.06042