Integration of Distributed Intrusion Detection Systems in IoT Infrastructure

Internet of Things (IoT) is an attractive innovation technology which utilized to interrelate all IoT devices worldwide with the help of the best high speed Internet. Nowadays, industries’ data are being transferred over heterogeneous IoT devices (e.g., smart house, smart watch, sensors, and so forth) connected with each other via power Internet. Nevertheless, this emerging innovation technology is under risks due to the lack of safe security. IoT network requires strong security to detect malicious behavior accurately. Intrusion Detection System (IDS) is a smart tool/software used to monitor input/output network traffic and generate an alarm message whenever malicious activities occurred. In this study, we build a smart IDS based on machine learning (ML) approaches using data mining tool known as Knime and Anaconda-Python to classify intrusions in IoT network. The evaluation of the model is conducted based on two tools for efficiently predicting and classifying real-world network intrusions from Coburg Intrusion Detection Dataset (CIDDS-001) for better decision making.