An Adaptive Model Filtering Algorithm Based on Grubbs Test in Federated Learning

An Adaptive Model Filtering Algorithm Based on Grubbs Test in Federated Learning

Federated learning has been popular for its ability to train centralized models while protecting clients’ data privacy. However, federated learning is highly susceptible to poisoning attacks, which can result in a decrease in model performance or even make it unusable. Most existing defense methods...

Full description

Bibliographic Details
Main Authors: Wenbin Yao, Bangli Pan, Yingying Hou, Xiaoyong Li, Yamei Xia
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Entropy
Subjects:
federated learning
byzantine-robust
poison attack defense
non-IID
Online Access:https://www.mdpi.com/1099-4300/25/5/715

Internet

https://www.mdpi.com/1099-4300/25/5/715

Similar Items