FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders
Hanlin Gu, Lixin Fan, Xingxing Tang, Qiang Yang

TL;DR
FedCut introduces a spectral analysis framework that effectively detects Byzantine colluders in federated learning, significantly improving model robustness against malicious attacks through community detection techniques.
Contribution
The paper presents a novel spectral analysis approach using community detection to identify Byzantine colluders, enhancing robustness in federated learning systems.
Findings
FedCut achieves 2.1% to 16.5% higher average model performance under attacks.
It outperforms existing methods with 17.6% to 69.5% better worst-case performance.
The framework converges with bounded errors, ensuring reliable detection.
Abstract
This paper proposes a general spectral analysis framework that thwarts a security risk in federated Learning caused by groups of malicious Byzantine attackers or colluders, who conspire to upload vicious model updates to severely debase global model performances. The proposed framework delineates the strong consistency and temporal coherence between Byzantine colluders' model updates from a spectral analysis lens, and, formulates the detection of Byzantine misbehaviours as a community detection problem in weighted graphs. The modified normalized graph cut is then utilized to discern attackers from benign participants. Moreover, the Spectral heuristics is adopted to make the detection robust against various attacks. The proposed Byzantine colluder resilient method, i.e., FedCut, is guaranteed to converge with bounded errors. Extensive experimental results under a variety of settings…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Security and Intrusion Detection · HIV, Drug Use, Sexual Risk
