FLUIDS: Federated Learning with semi-supervised approach for Intrusion Detection System - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

FLUIDS: Federated Learning with semi-supervised approach for Intrusion Detection System

Résumé

In this paper, we present FLUIDS, a Federated Learning with semi-sUpervised approach for Intrusion Detection System. FLUIDS formulates the intrusion detection into a semisupervised learning where both supervised learning (using labeled data) and unsupervised learning (no label data) are combined in a collaborative way. The combination of federated learning and semi-supervised Learning allows the solution to: better preserve the privacy, improve training and inference efficiency, achieve better accuracy, and be cheaper to deploy.
Fichier principal
Vignette du fichier
1570772923 final (3).pdf (345.94 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03496518 , version 1 (21-12-2021)

Identifiants

  • HAL Id : hal-03496518 , version 1

Citer

Ons Aouedi, Kandaraj Piamrat, Guillaume Muller, Kamal Singh. FLUIDS: Federated Learning with semi-supervised approach for Intrusion Detection System. IEEE Consumer Communications & Networking Conference (CCNC), Jan 2022, Los Angeles (virtual), United States. ⟨hal-03496518⟩
141 Consultations
385 Téléchargements

Partager

Gmail Facebook X LinkedIn More