FedGDD: Defending Federated Learning Against Targeted Model Poisoning Sybil Attacks Based on Gradient Drift Detection
IEEE Transactions on Reliability · 2026 · 75 · 2052-2066
DOI: 10.1109/tr.2026.3696364 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Reliability, 2026. Verfasst von Qi Xiong und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: CloudTech RMIT Green Bitcoin Joint Research Program.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- CloudTech RMIT Green Bitcoin Joint Research Program
Zitieren
APA
Xiong, Q., Dong, H., Sohrabi, N., & Tari, Z. (2026). FedGDD: Defending Federated Learning Against Targeted Model Poisoning Sybil Attacks Based on Gradient Drift Detection. IEEE Transactions on Reliability, 75, 2052-2066. https://doi.org/10.1109/tr.2026.3696364
Vancouver
Xiong Q, Dong H, Sohrabi N, Tari Z. FedGDD: Defending Federated Learning Against Targeted Model Poisoning Sybil Attacks Based on Gradient Drift Detection. IEEE Transactions on Reliability. 2026;75:2052-2066. doi:10.1109/tr.2026.3696364
BibTeX
@article{Xiong2026,
author = {Xiong, Qi and Dong, Hai and Sohrabi, Nasrin and Tari, Zahir},
title = {FedGDD: Defending Federated Learning Against Targeted Model Poisoning Sybil Attacks Based on Gradient Drift Detection},
journal = {IEEE Transactions on Reliability},
year = {2026},
volume = {75},
pages = {2052--2066},
doi = {10.1109/tr.2026.3696364}
}
EUVIMED