FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection

Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. The decentralized nature of FL makes it susceptible to adversarial attacks, especially backdoor insertion during training. Recently, the edge-case backdoor attack employing the tail of the data dis...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-04
Hauptverfasser:	Nguyen, Thuy Dung, Nguyen, Anh Duy, Kok-Seng Wong, Pham, Huy Hieu, Nguyen, Thanh Hung, Phi Le Nguyen, Truong Thao Nguyen
Format:	Artikel
Sprache:	eng
Schlagworte:	Clients Cutting resistance Federated learning Inspection
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!