Anomaly Detection System for Smart Home using Machine Learning

Internet of things (IoT) networks are present in a variety of industries and have become an integral part of our lives. With the advancement in technology, there has also been an increase in threats and security risks to IoT devices. In the case of Smart home networks, most of the IoT devices are vulnerable and have limited processing power. Whenever a new IoT device connects to the home network or any given network, it must be quickly managed and secured using the relevant security measures. This paper proposes to build a system that can classify devices connected as IoT or Non-IoT devices using machine learning (ML) and provide an Anomaly detection system for monitoring any anomalies or suspicious activities on the network. The ML model has been trained on a dataset and will be implemented on a test bed that consists of IoT, Non-IoT devices, a connector, and a hub to check the efficiency of the model. The F-measure will be calculated to compare the performance of different machine learning algorithms. The proposed model will also be integrated with a commercial software solution called Enigma Glass with an end-user dashboard providing analytics, visualizations, and notifications regarding the smart home network.