Metrics and Strategies for Adversarial Mitigation in Federated Learning-based Intrusion Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Metrics and Strategies for Adversarial Mitigation in Federated Learning-based Intrusion Detection

Résumé

Since its introduction in 2016, federated learning (FL) has been used in multiple domains, such as intrusion detection. However, FL literature shows that the heterogeneity of most real-world FL applications makes it difficult for clients to converge in a suitable global model. Furthermore, as a collaborative system, FL is vulnerable to attacks, such as model poisoning. While strategies have been identified in the literature, they often rely on the assumption that the data distribution among participants is homogeneous. In this paper, we review the current challenges in clustering and adversarial mitigation in heterogeneous FL, and propose different strategies to address them. Namely, we present a cross-evaluation framework for exhaustive gathering, and a set of algorithmic countermeasures based on principal component analysis. We show preliminary results of our clustering mechanism, which validates the effectiveness of the cross-evaluation framework.
Fichier non déposé

Dates et versions

hal-04275272 , version 1 (08-11-2023)

Identifiants

  • HAL Id : hal-04275272 , version 1

Citer

Léo Lavaur, Pierre-Marie Lechevalier, Yann Busnel, Marc-Oliver Pahl, Fabien Autrel. Metrics and Strategies for Adversarial Mitigation in Federated Learning-based Intrusion Detection. RESSI 2023 : Rendez-vous de la Recherche et de l'Enseignement de la Sécurité des Systèmes d'Information, May 2023, Neuvy-sur-Barangeon, France. ⟨hal-04275272⟩
25 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More