FLARE: A Backdoor Attack to Federated Learning with Refined Evasion

Qingya Wang, Yi Wu, Haojun Xuan () and Huishu Wu
Additional contact information
Qingya Wang: Faculty of Law, University of Montreal, 2900 Edouard Montpetit Blvd, Montreal, QC H3T 1J4, Canada
Yi Wu: China Academy of Information and Communications Technology, Beijing 100191, China
Haojun Xuan: School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing 100081, China
Huishu Wu: Faculty of Law, University of Montreal, 2900 Edouard Montpetit Blvd, Montreal, QC H3T 1J4, Canada

Mathematics, 2024, vol. 12, issue 23, 1-14

Abstract: Federated Learning (FL) is vulnerable to backdoor attacks in which attackers inject malicious behaviors into the global model. To counter these attacks, existing works mainly introduce sophisticated defenses by analyzing model parameters and utilizing robust aggregation strategies. However, we find that FL systems can still be attacked by exploiting their inherent complexity. In this paper, we propose a novel three-stage backdoor attack strategy named FLARE: A Backdoor Attack to Federated Learning with Refined Evasion, which is designed to operate under the radar of conventional defense strategies. Our proposal begins with a trigger inspection stage to leverage the initial susceptibilities of FL systems, followed by a trigger insertion stage where the synthesized trigger is stealthily embedded at a low poisoning rate. Finally, the trigger is amplified to increase the attack’s success rate during the backdoor activation stage. Experiments on the effectiveness of FLARE show significant enhancements in both the stealthiness and success rate of backdoor attacks across multiple federated learning environments. In particular, the success rate of our backdoor attack can be improved by up to 45× compared to existing methods.

Keywords: federated learning; backdoor attacks; trigger inspection; poisoning rate (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/23/3751/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/23/3751/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:23:p:3751-:d:1532012

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().