Securing Smart Healthcare: Intrusion Detection in IoMT Networks Using Deep Learning

Abstract

With the exponential growth of the Internet of Medical Things (IoMT), healthcare systems are increasingly vulnerable to a wide array of cyber threats that can jeopardize patient safety, data privacy, and operational integrity. Traditional security mechanisms often fall short in identifying sophisticated or novel attack patterns. To address this issue, we propose a deep learning-based intrusion detection system (IDS) that leverages Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) to detect malicious activity within IoMT network traffic. The system is evaluated using the CICIoMT2024 dataset, which simulates real-world IoMT environments. We conduct three levels of classification: binary (attack vs. normal), 6-class (category-level attacks), and 19-class (specific attack types). Each model is assessed using performance metrics including accuracy, precision, recall, and F1-score. Our results indicate that CNNs consistently outperform RNNs, particularly in binary and category-level classifications, achieving high accuracy and robustness. The study demonstrates the effectiveness of deep learning models in enhancing IoMT network security and provides a practical framework for deploying intelligent, real-time IDS solutions in healthcare infrastructures.