Towards efficient and certified recovery from poisoning attacks in federated learning

Towards efficient and certified recovery from poisoning attacks in federated learning

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model. Although various methods exist for detecting those clients in FL, identifying malicious clients requires sufficient model updates, and hence by the time malicious...

Full description

Bibliographic Details
Main Authors: Jiang, Yu, Shen, Jiyuan, Liu, Ziyao, Tan, Chee Wei, Lam, Kwok-Yan
Other Authors: College of Computing and Data Science
Format: Journal Article
Language:English
Published: 2025
Subjects:
Computer and Information Science
Federated learning
Poisoning attack
Online Access:https://hdl.handle.net/10356/182606

Internet

https://hdl.handle.net/10356/182606

Similar Items