Generating IoT Edge Network Datasets based on the TON_IoT Telemetry Dataset
Georgios Zachos, Ismael Essop, Γεώργιος Μαντάς, Kyriakos Porfyrakis, José Ribeiro, Jonathan Rodrı́guez · 2021
The rise of the Internet of Things (IoT) and Industrial IoT (IIoT), over the past few years, has been beneficial for the citizens, societies and industry. However, their resource-constrained and heterogenous nature renders them vulnerable to a wide range of threats. Therefore, novel security mechanisms, such as accurate and efficient anomaly-based intrusion detection systems (AIDSs), are required to be developed before IoT/IIoT networks reach their full potential in the market. However, there is a lack of up-to-date, representative and well-structured IoT/IIoT-specific datasets that are publicly available to the research community and constitute benchmark datasets for effective training and evaluation of Machine Learning models suitable for AIDSs in IoT/IIoT networks. Contribution to filling this research gap is of utmost importance and toward this direction the novel “TON_IoT Telemetry” dataset was recently published. Taking the opportunity to explore further this dataset, we targeted at its network-related part so as to generate IoT edge network specific datasets for effective development of more accurate and efficient IoT/IIoT-specific AIDSs. Therefore, in this paper, we present the methodology we followed to generate a set of IoT edge network specific datasets based on the “ToN_IoT Telemetry” dataset.