In recent times, the number of Internet of Things (IoT) devices and the applications developed for these devices has increased; as a result, these IoT devices are targeted by many malicious activities that cause potential damage in many smart infrastructures. A technique is required to appropriately classify anomalous activities to minimize the impact of these activities. The IoT networks are difficult to analyze and test because of the lack of sufficient well-structured IoT datasets for anomaly-based intrusion detection. In this paper, we present a technique we have used to generate a new Botnet dataset, from an existing one, for anomalous activity detection in IoT networks. The new IoT botnet dataset has a wider network and flow-based features. A flow-based Intrusion Detection System (IDS) can be analyzed and tested using flow-based features. Finally, we use different machine learning methods to test the accuracy of our proposed dataset. We also test the accuracy of our proposed dataset through various feature correlation and the methodology for recursive feature elimination. Our proposed IoT botnet dataset provides a ground to analyze and evaluate anomalous activity detection model for IoT networks. We have shared the newly generated Botnet dataset publicly.
Free use of the IoT Botnet Dataset for academic research purposes is hereby granted in perpetuity. please cite the following paper that has the dataset’s details.
I. Ullah and Q. H. Mahmoud, "A Technique for Generating a Botnet Dataset for Anomalous Activity Detection in IoT Networks," 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, 2020, pp. 134-140, doi: 10.1109/SMC42975.2020.9283220.