Brute Force Attacks Detection on IoT Networks using Deep Learning Techniques

Abstract

The Internet of Things (IoT) sector is expanding quickly, and its applications are becoming more prevalent in our day-to-day lives. Various protocols are used to control communication between IoT devices. The Message Queue Telemetry Protocol (MQTT), a simple and trustworthy communication protocol, is a well-known illustration of these protocols. However, MQTT-IoT networks have been the target of cyberattacks, which highlights the need for an effective intrusion detection system for spotting such attempts. The brute force attack is a common sort of such attacks. We suggest deep learning in this study as a means of automatically identifying brute force assaults on MQTT-IoT networks. We train the deep learning model with a large number of instances and a flow-based feature using the MQTT-IoT-IDS2020 dataset. With more than 99% accuracy in differentiating between regular and brute force attacks, the classification model is quite accurate in detecting such attempts