Practical attribute reconstruction attack against federated learning

Practical attribute reconstruction attack against federated learning

Existing federated learning (FL) designs have been shown to exhibit vulnerabilities which can be exploited by adversaries to compromise data privacy. However, most current works conduct attacks by leveraging gradients calculated on a small batch of data. This setting is not realistic as gradients ar...

Full description

Bibliographic Details
Main Authors: Chen, Chen, Lyu, Lingjuan, Yu, Han, Chen, Gang
Other Authors: College of Computing and Data Science
Format: Journal Article
Language:English
Published: 2024
Subjects:
Computer and Information Science
Artificial intelligence
Federated learning
Online Access:https://hdl.handle.net/10356/179056

Internet

https://hdl.handle.net/10356/179056

Similar Items