We elaborate on the dataset collected from our testbed developed at Washington University in St. Louis, to perform real-world IIoT operations, carrying out attacks that are more prelevant against IIoT systems. This dataset is to be utilized in the research of AI/ML based security solutions to tackle the intrusion problem.
Our IIoT network security dataset has been released to support the research community for a more realistic and diverse data collection in different extensive sub-fields of AI for IIoT that there is an increasing interest in, such as explainable AI, distributed AI, etc.
Provided dataset is cleased, pre-processed, and ready to use. The users may modify as they wish, but please cite the dataset as below:
M. Zolanvari, M. A. Teixeira, L. Gupta, K. M. Khan, and R. Jain. "Machine learning-based network vulnerability analysis of Industrial Internet of Things," in IEEE Internet of Things Journal 6 (2019), pp. 6822-6834.
If interested, below papers present our three other research papers utilizing this dataset in the case studies.
- M. Zolanvari, M. Teixeira, R. Jain, “Effect of Imbalanced Datasets on Security of Industrial IoT Using Machine Learning,” in Proceedings of IEEE ISI (Intelligence and Security Informatics), November 2018.
- M. Zolanvari, Z. Yang, K. M. Khan, R. Jain, and N. Meskin, "TRUST XAI: A Novel Model for Explainable AI with An Example Using IIoT Security," in IEEE Internet of Things Journal , September 2021.
- M. Zolanvari, A. Ghubaish, and R. Jain, "ADDAI: Anomaly Detection using Distributed AI," in Proceedings of IEEE ICNSC (International Conference on Networking, Sensing and Control), October 2021.