Saved in:
Bibliographic Details
Main Authors: Han, Xingshuo, Zhang, Xuanye, Lan, Xiang, Wang, Haozhao, Xu, Shengmin, Ren, Shen, Zeng, Jason, Wu, Ming, Heinrich, Michael, Zhang, Tianwei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.16167
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911043518726144
author Han, Xingshuo
Zhang, Xuanye
Lan, Xiang
Wang, Haozhao
Xu, Shengmin
Ren, Shen
Zeng, Jason
Wu, Ming
Heinrich, Michael
Zhang, Tianwei
author_facet Han, Xingshuo
Zhang, Xuanye
Lan, Xiang
Wang, Haozhao
Xu, Shengmin
Ren, Shen
Zeng, Jason
Wu, Ming
Heinrich, Michael
Zhang, Tianwei
contents By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Federated Learning. Although Scaffold achieves significant performance improvements, we show that this superiority is at the cost of increased security vulnerabilities. Specifically, this paper presents BadSFL, the first backdoor attack targeting Scaffold, which turns benign clients into accomplices to amplify the attack effect. The core idea of BadSFL is to uniquely tamper with the control variate to subtly steer benign clients' local gradient updates towards the attacker's poisoned direction, effectively turning them into unwitting accomplices and significantly enhancing the backdoor persistence. Additionally, BadSFL leverages a GAN-enhanced poisoning strategy to enrich the attacker's dataset, maintaining high accuracy on both benign and backdoored samples while remaining stealthy. Extensive experiments demonstrate that BadSFL achieves superior attack durability, maintaining effectiveness for over 60 global rounds, lasting up to three times longer than existing baselines even after ceasing malicious model injections.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16167
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
Han, Xingshuo
Zhang, Xuanye
Lan, Xiang
Wang, Haozhao
Xu, Shengmin
Ren, Shen
Zeng, Jason
Wu, Ming
Heinrich, Michael
Zhang, Tianwei
Machine Learning
By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Federated Learning. Although Scaffold achieves significant performance improvements, we show that this superiority is at the cost of increased security vulnerabilities. Specifically, this paper presents BadSFL, the first backdoor attack targeting Scaffold, which turns benign clients into accomplices to amplify the attack effect. The core idea of BadSFL is to uniquely tamper with the control variate to subtly steer benign clients' local gradient updates towards the attacker's poisoned direction, effectively turning them into unwitting accomplices and significantly enhancing the backdoor persistence. Additionally, BadSFL leverages a GAN-enhanced poisoning strategy to enrich the attacker's dataset, maintaining high accuracy on both benign and backdoored samples while remaining stealthy. Extensive experiments demonstrate that BadSFL achieves superior attack durability, maintaining effectiveness for over 60 global rounds, lasting up to three times longer than existing baselines even after ceasing malicious model injections.
title Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
topic Machine Learning
url https://arxiv.org/abs/2411.16167