Defending Byzantine attacks in ensemble federated learning: A reputation-based phishing approach

Beibei Li, Peiran Wang, Zerui Shao, Ao Liu, Yukun Jiang, Yizhou Li

Abstract: Highlights•Design a new federated learning architecture supporting various deep learning models.•Craft a ‘phishing’ method to detect Byzantine attacks in federated learning.•Present a Bayesian inference-based mechanism to evaluate the reputation of clients.