Enhancing IoT network defense: advanced intrusion detection via ensemble learning techniques.

The Internet of things (IoT) has evolved significantly, automating daily activities by connecting numerous devices. However, this growth has increased cybersecurity threats, compromising data integrity. To address this, intrusion detection systems (IDSs) have been developed, mainly using predefined attack patterns. With rising cyber-attacks, improving IDS effectiveness is crucial, and machine learning is a key solution. This research enhances IDS capabilities by introducing binary attack identification and multiclass attack categorization for IoT traffic, aiming to improve IDS performance. Our framework uses the 'BoT-IoT' and 'TON-IoT' datasets, which include various IoT network traffic and cyber-attack scenarios, such as DDoS and data infiltration, to train machine learning and ensemble models. Specifically, it combines three machine learning models-decision tree, resilient backpropagation (RProp) multilayer perceptron (MLP), and logistic regression-into ensemble methods like voting and stacking to improve prediction accuracy and reduce detection errors. These ensemble classifiers outperform individual models, demonstrating the benefit of diverse learning techniques. Our framework achieves high accuracy, with 99.99% for binary classification on the BoT-IoT dataset and 97.31% on the ToN-IoT dataset. For multiclass classification, it achieves 99.99% on BoT-IoT and 96.32% on ToN-IoT, significantly enhancing IDS effectiveness against IoT cybersecurity threats. [ABSTRACT FROM AUTHOR]