The Detection of IoT Botnet using Machine Learning on IoT-23 Dataset
Falaq Jeelani, Dhajvir Singh, Ankit Maithani, Shubhi Gupta
Abstract
As smart devices and the Internet develop; the Internet of Things (IoT) technologies have become an important factor in our life. IoT helps manufactory companies to monitor the status of every machine in real time, the quality of products and the environment variables within the factory. This not only allows managers to reduce the risk of damages and losses, also help to make decision from a higher overall standpoint. In addition, IoT has changed people's life and behavior. People are now relied on IoT devices and services morethan ever. However, anomalies can cause security and safety issues for an IoT network. It is important to detect anomalies and alarm user to prevent damages or losses. We proposed in this study that abnormalities in a network be detected using Machine Learning and Deep Learning methodologies. The tests were carried out using the IoT-23 dataset. Decision tree algorithm obtained the highest accuracy for the proposed model. These models' performance and time costs are evaluated to find the optimum algorithm that delivers great performance in less time.