<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Publication:
Byzantines can also learn from history: fall of centered clipping in federated learning

Loading...
Thumbnail Image

School / College / Institute

Item type:Organizational Unit,
Item type:Organizational Unit,
Item type:Organizational Unit,

Program

Organization Authors

Co-Authors

Özfatura, Emre

Gündüz, Deniz

Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks.

Source

Publisher

IEEE-Inst Electrical Electronics Engineers Inc

Citation

item.page.haspartof

Source

IEEE Transactions on Information Forensics and Security

item.page.ispartofseries

item.page.edition

DOI

10.1109/TIFS.2023.3345171

item.page.datauri

item.page.link

Rights

 

Copyrights Note

Rights and licensing

 

Endorsement

Review

Supplemented By

Referenced By

Related Patent

Related Goal

Google Scholar
Scholar'da Ara ↗
Altmetric
Dimensions
PlumX Metrikleri
BIP! Indicators