Securing federated learning: a defense strategy against targeted data poisoning attack

Securing federated learning: a defense strategy against targeted data poisoning attack

Abstract Ensuring the security and integrity of Federated Learning (FL) models against adversarial attacks is critical. Among these threats, targeted data poisoning attacks, particularly label flipping, pose a significant challenge by undermining model accuracy and reliability. This paper investigat...

Full description

Bibliographic Details
Main Authors: Ansam Khraisat, Ammar Alazab, Moutaz Alazab, Tony Jan, Sarabjot Singh, Md. Ashraf Uddin
Format: Article
Language:English
Published: Springer 2025-02-01
Series:Discover Internet of Things
Subjects:
Attack detection
Federated learning
Poisoning attacks
Malware
Online Access:https://doi.org/10.1007/s43926-025-00108-6

Internet

https://doi.org/10.1007/s43926-025-00108-6

Similar Items