BaFFLe: Backdoor Detection via Feedback-based Federated Learning

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive techniques. In this paper, we propose Backdoor detec...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the International Conference on Distributed Computing Systems S. 852 - 863
Hauptverfasser:	Andreina, Sebastien, Marson, Giorgia Azzurra, Mollering, Helen, Karame, Ghassan
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.07.2021
Schlagworte:	Adaptation models backdoor attacks Collaborative work Computational modeling Conferences Data models federated learning Feedback loop security Training
ISSN:	2575-8411
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!