Beta Hebbian Learning for intrusion detection in networks with MQTT Protocols for IoT devices

Abstract This paper aims to enhance security in IoT device networks through a visual tool that utilizes three projection techniques, including Beta Hebbian Learning (BHL), t-distributed Stochastic Neighbor Embedding (t-SNE) and ISOMAP, in order to facilitate the identification of network attacks by...

Full description

Saved in:
Bibliographic Details
Published inLogic journal of the IGPL Vol. 32; no. 2; pp. 352 - 365
Main Authors Michelena, Álvaro, García Ordás, María Teresa, Aveleira-Mata, José, Marcos del Blanco, David Yeregui, Timiraos Díaz, Míriam, Zayas-Gato, Francisco, Jove, Esteban, Casteleiro-Roca, José-Luis, Quintián, Héctor, Alaiz-Moretón, Héctor, Luis Calvo-Rolle, José
Format Journal Article
LanguageEnglish
Published Oxford University Press 25.03.2024
Subjects
MQTT
t-SNE
Beta Hebbian Learning
cyberattack
ISOMAP
IoT
Online AccessGet full text
ISSN1367-0751
1368-9894
DOI10.1093/jigpal/jzae013

Cover

More Information
Summary:Abstract This paper aims to enhance security in IoT device networks through a visual tool that utilizes three projection techniques, including Beta Hebbian Learning (BHL), t-distributed Stochastic Neighbor Embedding (t-SNE) and ISOMAP, in order to facilitate the identification of network attacks by human experts. This work research begins with the creation of a testing environment with IoT devices and web clients, simulating attacks over Message Queuing Telemetry Transport (MQTT) for recording all relevant traffic information. The unsupervised algorithms chosen provide a set of projections that enable human experts to visually identify most attacks in real-time, making it a powerful tool that can be implemented in IoT environments easily.
ISSN:1367-0751
1368-9894
DOI:10.1093/jigpal/jzae013