DART: A Solution for decentralized federated learning model robustness analysis

Federated Learning (FL) has emerged as a promising approach to address privacy concerns inherent in Machine Learning (ML) practices. However, conventional FL methods, particularly those following the Centralized FL (CFL) paradigm, utilize a central server for global aggregation, which exhibits limit...

Full description

Bibliographic Details
Published in:Array
Main Authors: Chao Feng, Alberto Huertas Celdrán, Jan von der Assen, Enrique Tomás Martínez Beltrán, Gérôme Bovet, Burkhard Stiller
Format: Article
Language:English
Published: Elsevier 2024-09-01
Subjects:
Decentralized federated learning
Poisoning attack
Cybersecurity
Model robustness
Online Access:http://www.sciencedirect.com/science/article/pii/S2590005624000262

Internet

http://www.sciencedirect.com/science/article/pii/S2590005624000262

Similar Items