Detecting IoT Attacks Using an Ensemble Machine Learning Model

Malicious attacks are becoming more prevalent due to the growing use of Internet Things (IoT) devices in homes, offices, transportation, healthcare, and other locations. By incorporating fog computing into IoT, can be detected a short amount time, as distance between IoT is smaller than cloud. Machine learning frequently used for detection huge data available from devices. However, problem that may not have enough resources, such processing power memory, detect timely manner. This paper proposes an approach offload machine model selection task cloud real-time prediction nodes. Using proposed method, based on historical data, ensemble built cloud, followed by The tested using NSL-KDD dataset. results show effectiveness terms several performance measures, execution precision, recall, accuracy, ROC (receiver operating characteristic) curve.