Detection of IoT Botnet Cyber Attacks using Machine Learning

Abstract

Since they were first used, systems have faced threats from viruses, worms, and hacking attacks. In 2018, there were more devices online than there were people, and this tendency will continue to grow, with an estimated 80 billion devices online by 2024. It is difficult to secure this equipment and the data that flows between them since IoT botnet attacks (IBA) are becoming more and more common. Potential hackers for data theft and cyberattacks have been enticed by the overwhelming quantity and omnipresent presence. One of the biggest issues with the Internet of Things is security. The main goal of this research project is to develop a workable machine learning algorithm-based model to identify and counteract botnet-based attacks on IoT networks. The suggested model addresses the security concern of the dangers provided by bots. The BoT-IoT dataset was used to train a variety of machine learning techniques, including linear regression, logistic regression, K-Nearest Neighbor (KNN), and SVM models. The performance of the system's results in an F-measure of: 1) 98.0%, 2) 99.0%, and 3) 99.0%. 4) 99.0%. This demonstrates that the proposed models can automatically separate between network activities is malicious or normal.