SWIoTA: Anomaly Detection for Distributed Ledger Technology-Based Internet of Things (IOTA) Using Sliding Window (SW) Technique - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2022

SWIoTA: Anomaly Detection for Distributed Ledger Technology-Based Internet of Things (IOTA) Using Sliding Window (SW) Technique

Sathish Kumar
  • Fonction : Auteur
  • PersonId : 1417399
Norman Ahmed
  • Fonction : Auteur
  • PersonId : 1417400
Anastasios Bikos
  • Fonction : Auteur
  • PersonId : 1417401

Résumé

IOTA is a Digital Ledger Technology (DLT) prototype for IoT applications that has attracted a rising popularity in recent years. One issue that acts as obstacle to its widespread adoption are the cybersecurity concerns. Some of the security concerns in IOTA include Denial of Service (DoS) double spending, parasite attacks, and DDoS attacks. In this work, we developed a Machine-Learning (ML) approach to create security threat index that can be utilized to proactively provide defenses to the IOTA decentralized infrastructure as well as individual nodes against potential compromises. Our approach is established on the sliding window customized technique to classify the data generated from the DAG-based nodes for cybersecurity anomaly detection. To validate the approach, we implemented “DoS attacks” threat model in the DLT-based IoT environment using Raspberry Pi devices and experimented our security methods and algorithms in this environment. The preliminary experimental results are promising.
Fichier principal
Vignette du fichier
AICT 665_174.pdf (1.05 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04704231 , version 1 (20-09-2024)

Licence

Identifiants

Citer

Sathish Kumar, Norman Ahmed, Anastasios Bikos. SWIoTA: Anomaly Detection for Distributed Ledger Technology-Based Internet of Things (IOTA) Using Sliding Window (SW) Technique. 5th IFIP International Internet of Things Conference (IFIPIoT), Oct 2022, Amsterdam, Netherlands. pp.177-194, ⟨10.1007/978-3-031-18872-5_11⟩. ⟨hal-04704231⟩
21 Consultations
0 Téléchargements

Altmetric

Partager

More