FedSV: Byzantine-Robust Federated Learning via Shapley Value

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Otmani, Khaoula, Elazouzi, Rachid, Labatut, Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915171219275776
author Otmani, Khaoula
Elazouzi, Rachid
Labatut, Vincent
author_facet Otmani, Khaoula
Elazouzi, Rachid
Labatut, Vincent
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17526
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedSV: Byzantine-Robust Federated Learning via Shapley Value
Otmani, Khaoula
Elazouzi, Rachid
Labatut, Vincent
Machine Learning
Cryptography and Security
Computer Science and Game Theory
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.
title FedSV: Byzantine-Robust Federated Learning via Shapley Value
topic Machine Learning
Cryptography and Security
Computer Science and Game Theory
url https://arxiv.org/abs/2502.17526