FedSV: Byzantine-Robust Federated Learning via Shapley Value - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

FedSV: Byzantine-Robust Federated Learning via Shapley Value

Résumé

In Federated Learning (FL), several clients jointly learn a machine learning model: each client maintains a local model for its local learning dataset, while a master server maintains a global model by aggregating the local models of the client devices. However, the repetitive communication between server and clients leaves room for attacks aimed at compromising the integrity of the global model, causing errors in its targeted predictions. In response to such threats on FL, various defense measures have been proposed in the literature. In this paper, we present a powerful defense against malicious clients in FL, called FedSV, using the Shapley Value (SV), which has been proposed recently to measure user contribution in FL by computing the marginal increase of average accuracy of the model due to the addition of local data of a user. Our approach makes the identification of malicious clients more robust, since during the learning phase, it estimates the contribution of each client according to the different groups to which the target client belongs. FedSV’s effectiveness is demonstrated by extensive experiments on MNIST datasets in a cross-silo context under various attacks.
Fichier principal
Vignette du fichier
Article_FedSV-5.pdf (615.07 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04512814 , version 1 (20-03-2024)
hal-04512814 , version 2 (16-04-2024)

Identifiants

  • HAL Id : hal-04512814 , version 2

Citer

Khaoula Otmani, Rachid Elazouzi, Vincent Labatut. FedSV: Byzantine-Robust Federated Learning via Shapley Value. IEEE International Conference on Communications, Jun 2024, Denver (CO), United States. ⟨hal-04512814v2⟩

Collections

UNIV-AVIGNON LIA
7 Consultations
11 Téléchargements

Partager

Gmail Facebook X LinkedIn More