Understanding Distributed Poisoning Attack in Federated Learning

Federated learning is inherently vulnerable to poisoning attacks, since no training samples will be released to and checked by trustworthy authority. Poisoning attacks are widely investigated in centralized learning paradigm, however distributed poisoning attacks, in which more than one attacker col...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS) S. 233 - 239
Hauptverfasser:	Cao, Di, Chang, Shan, Lin, Zhijian, Liu, Guohua, Sun, Donghong
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.12.2019
Schlagworte:	attack success rate defense distributed poisoning attack federated learning label-flipping
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!