Attacks and countermeasures on federated learning via historical knowledge modeling

Abstract Federated learning has emerged as a promising paradigm for privacy-preserving multi-source data fusion. However, its distributed nature makes it vulnerable to poisoning attacks. Malicious clients inject poisoned noises into their local models, severely degrading the global model’s performan...

Full description

Saved in:
Bibliographic Details
Main Authors: Songsong Zhang, Zhengliang Jiang, Hang Gao, Suying Gui, Tiegang Gao
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00115-1
Tags: Add Tag
No Tags, Be the first to tag this record!