Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives

Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives

Abstract Empirical attacks on Federated Learning (FL) systems indicate that FL is fraught with numerous attack surfaces throughout the FL execution. These attacks can not only cause models to fail in specific tasks, but also infer private information. While previous surveys have identified the risks...

Full description

Bibliographic Details
Main Authors: Pengrui Liu, Xiangrui Xu, Wei Wang
Format: Article
Language:English
Published: SpringerOpen 2022-02-01
Series:Cybersecurity
Subjects:
Federated learning
Security and privacy threats
Multi-phases
Inference attacks
Poisoning attacks
Evasion attacks
Online Access:https://doi.org/10.1186/s42400-021-00105-6

Internet

https://doi.org/10.1186/s42400-021-00105-6

Similar Items