Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability
The Internet of Medical Things (IoMT) brings advanced patient monitoring and predictive analytics to healthcare but also raises cybersecurity and data privacy issues. This paper introduces a deep-learning model for IoMT intrusion detection, utilizing the WUSTL EHMS 2020 dataset, which focuses on cyb...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/115682/ http://psasir.upm.edu.my/id/eprint/115682/1/115682.pdf |
| Summary: | The Internet of Medical Things (IoMT) brings advanced patient monitoring and predictive analytics to healthcare but also raises cybersecurity and data privacy issues. This paper introduces a deep-learning model for IoMT intrusion detection, utilizing the WUSTL EHMS 2020 dataset, which focuses on cyber threats like man-in-the-middle attacks and data injection. Our sequential model, trained with TensorFlow, surpasses traditional predictive accuracy and efficiency methods. It achieves 99% accuracy with reduced loss and excels in precision, recall, F1 Score, and ROC AUC. The model uses 25 key features from 45, preventing overfitting and addressing data leakage in preprocessing. These steps ensure the model's reliability for IoMT cybersecurity, demonstrating its effectiveness in real-world scenarios. |
|---|