FUBA: Federated uncovering of backdoor attacks for heterogeneous data - Laboratoire d'Intégration des Systèmes et des Technologies Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

FUBA: Federated uncovering of backdoor attacks for heterogeneous data

Résumé

This paper proposes a post-training defense against pattern-triggered backdoor attacks in federated learning contexts. This approach relies first on the server estimating the attack pattern. The server then provides the estimated pattern to the end-users, who use it directly on their local data to mitigate backdoor attacks during inference time. This scheme offers an improvement over the existing approaches by demonstrating robustness to data heterogeneity among users without needing a shared dataset or additional information from users and regardless of the number of malicious clients. Based on extensive comparison with existing state-of-the-art methods on well-known computer vision datasets, the proposed method is shown to succeed in mitigating backdoor attacks while preserving high accuracy on clean inputs.
Fichier principal
Vignette du fichier
IEEE_TPS_vf.pdf (762.49 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

cea-04576829 , version 1 (15-05-2024)

Identifiants

Citer

Fabiola Espinoza Castellon, Deepika Singh, Aurélien Mayoue, Cedric Gouy-Pailler. FUBA: Federated uncovering of backdoor attacks for heterogeneous data. TPS-ISA 2023 - 5th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, Nov 2023, Atlanta, United States. pp.55-63, ⟨10.1109/TPS-ISA58951.2023.00017⟩. ⟨cea-04576829⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More