XMeDNN: An Explainable Deep Neural Network System for Intrusion Detection in Internet of Medical Things
Summary
The rapid growth in the adoption of Internet of Things in various areas of our daily lives makes it an interesting target to malicious actors. One area that is witnessing accelerating growth in smart device adoption is health and medical services. The growth in Internet of Medical Things is triggering increased interest in privacy, confidentiality, and intrusion detection. In this paper, we present a deep neural network designed to detect attacks on Internet-of-Things devices in medical settings. The proposed system was tested using WUSTL-EHMS-2020 dataset. Tests showed that the proposed deep learning system can deliver excellent performance with accuracy 97.578%, and a false-positive rate of 3.12%.
Conference: 9th International Conference on Information Systems Security and Privacy
Location: Lisbon, Portugal
Date: February 22-24, 2023
Keywords
IoMT, IoT, DNN, Deep Neural Network, Intrusion Detection
Links
References
| APA | M. Alani, M., Mashatan, A., & Miri, A. (2023). XMeDNN: An explainable deep neural network system for intrusion detection in internet of medical things. Proceedings of the 9th International Conference on Information Systems Security and Privacy (pp. 144–151). |
|---|---|
| BibTeX | @INPROCEEDINGS{icissp23, author={Mohammed {M. Alani}. and Atefeh Mashatan. and Ali Miri.}, title={XMeDNN: An Explainable Deep Neural Network System for Intrusion Detection in Internet of Medical Things}, booktitle={Proceedings of the 9th International Conference on Information Systems Security and Privacy - ICISSP,}, year={2023}, pages={144-151}, publisher={SciTePress}, organization={INSTICC}, doi={10.5220/0011749200003405}, isbn={978-989-758-624-8}, issn={2184-4356}, } |
| IEEE | M. M. Alani, A. Mashatan, and A. Miri, “XMeDNN: An Explainable Deep Neural Network System for Intrusion Detection in Internet of Medical Things,” Proc. of the 9th Int. Conference on Inf. Systems Security and Privacy, Portugal, Lisbon, Feb. 22-24, 2023, pp. 144–151. |