Beta Hebbian Learning for intrusion detection in networks with MQTT Protocols for IoT devices
Álvaro Michelena, María Teresa García-Ordás, José Aveleira‐Mata, David Yeregui Marcos del Blanco, Míriam Timiraos, Francisco Zayas‐Gato, Esteban Jove, José‐Luis Casteleiro‐Roca, Héctor Quintián, Héctor Aláiz‐Moretón, JOSE LUIS CALVO ROLLE · Logic Journal of IGPL · 2024
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.