FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning

FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning

In response to the susceptibility of federated learning, which is based on a distributed training structure, to byzantine poisoning attacks from malicious clients, resulting in issues such as slowed or disrupted model convergence and reduced model accuracy, we propose a robust aggregation technique...

Full description

Bibliographic Details
Main Authors: Haitian Chen, Xuebin Chen, Lulu Peng, Ruikui Ma
Format: Article
Language:English
Published: MDPI AG 2023-10-01
Series:Electronics
Subjects:
federated learning
byzantine attacks
anomaly detection
credibility score
Online Access:https://www.mdpi.com/2079-9292/12/21/4463

Internet

https://www.mdpi.com/2079-9292/12/21/4463

Similar Items