EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust and Privacy-Preserving Federated Learning Against Malicious Clients: A Bulyan-Based Adaptive Differential Privacy Framework

Stuti Pandey, Onkar Singh, Ashish Pandey, Chandrasen Pandey

IEEE Access · 2025 · 13 · 139931-139943

DOI: 10.1109/access.2025.3596627 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Stuti Pandey und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Pandey, S., Singh, O., Pandey, A., & Pandey, C. (2025). Robust and Privacy-Preserving Federated Learning Against Malicious Clients: A Bulyan-Based Adaptive Differential Privacy Framework. IEEE Access, 13, 139931-139943. https://doi.org/10.1109/access.2025.3596627

Vancouver

Pandey S, Singh O, Pandey A, Pandey C. Robust and Privacy-Preserving Federated Learning Against Malicious Clients: A Bulyan-Based Adaptive Differential Privacy Framework. IEEE Access. 2025;13:139931-139943. doi:10.1109/access.2025.3596627

BibTeX
@article{Pandey2025,
  author = {Pandey, Stuti and Singh, Onkar and Pandey, Ashish and Pandey, Chandrasen},
  title = {Robust and Privacy-Preserving Federated Learning Against Malicious Clients: A Bulyan-Based Adaptive Differential Privacy Framework},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {139931--139943},
  doi = {10.1109/access.2025.3596627}
}
Kostenlos starten →