Sustainable Federated Learning in 6G Networks: The Case for Cybersecurity
IEEE Communications Magazine · 2026-08 · 64 (8) · 102-108
DOI: 10.1109/mcom.001.2500643 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Magazine, 2026-08. Verfasst von Gokcan Cantali und 3 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben.
Abstract (Originalsprache)
6G networks are expected to integrate distributed artificial intelligence methods, such as federated learning (FL), across layers from core infrastructure to end-user applications. While FL offers significant advantages by enabling collaborative model training without sharing local and sensitive data, its deployment in large-scale, complex 6G environments raises important sustainability and security concerns. In particular, FL's communication overhead, including carbon footprint, requires careful optimization to ensure sustainable operation. Simultaneously, the cybersecurity implications of sustainable FL remain underexplored. In this work, we examine the sustainability challenges associated with FL and analyze them from a cybersecurity perspective through a use case, highlighting relevant tradeoffs and key research directions for future 6G networks.
Zitieren
APA
Cantali, G., Soussi, W., Gur, G., & Stiller, B. (2026). Sustainable Federated Learning in 6G Networks: The Case for Cybersecurity. IEEE Communications Magazine, 64(8), 102-108. https://doi.org/10.1109/mcom.001.2500643
Vancouver
Cantali G, Soussi W, Gur G, Stiller B. Sustainable Federated Learning in 6G Networks: The Case for Cybersecurity. IEEE Communications Magazine. 2026;64(8):102-108. doi:10.1109/mcom.001.2500643
BibTeX
@article{Cantali2026,
author = {Cantali, Gokcan and Soussi, Wissem and Gur, Gurkan and Stiller, Burkhard},
title = {Sustainable Federated Learning in 6G Networks: The Case for Cybersecurity},
journal = {IEEE Communications Magazine},
year = {2026},
volume = {64},
number = {8},
pages = {102--108},
doi = {10.1109/mcom.001.2500643}
}
EUVIMED