SPFL: a self-purified federated learning method against poisoning attacks

SPFL: a self-purified federated learning method against poisoning attacks

While Federated learning (FL) is attractive for pulling privacy-preserving distributed training data, the credibility of participating clients and non-inspectable data pose new security threats, of which poisoning attacks are particularly rampant and hard to defend without compromising privacy, perf...

Full description

Bibliographic Details
Main Authors: Liu, Zizhen, He, Weiyang, Chang, Chip Hong, Ye, Jing, Li, Huawei, Li, Xiaowei
Other Authors: School of Electrical and Electronic Engineering
Format: Journal Article
Language:English
Published: 2024
Subjects:
Computer and Information Science
Federated learning
Poisoning attack
Deep neural network
Online Access:https://hdl.handle.net/10356/180384

Internet

https://hdl.handle.net/10356/180384

Similar Items