EUVIMEDEUVIMED entdecken
Crossref

FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders

Hanlin Gu, Lixin Fan, XingXing Tang, Qiang Yang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-09 · 46 (9) · 5905-5920

DOI: 10.1109/tpami.2024.3375287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-09. Verfasst von Hanlin Gu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 justify the superiority of FedCut, which demonstrates extremely robust model accuracy (MA) under various attacks. It was shown that FedCut's averaged MA is 2.1% to 16.5% better than that of the state of the art Byzantine-resilient methods. In terms of the worst-case model accuracy (MA), FedCut is 17.6% to 69.5% better than these methods.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Gu, H., Fan, L., Tang, X., & Yang, Q. (2024). FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(9), 5905-5920. https://doi.org/10.1109/tpami.2024.3375287

Vancouver

Gu H, Fan L, Tang X, Yang Q. FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(9):5905-5920. doi:10.1109/tpami.2024.3375287

BibTeX
@article{Gu2024,
  author = {Gu, Hanlin and Fan, Lixin and Tang, XingXing and Yang, Qiang},
  title = {FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {9},
  pages = {5905--5920},
  doi = {10.1109/tpami.2024.3375287}
}
Kostenlos starten →