Enhanced Internet of Medical Things Security: Evaluating Machine Learning and Deep Learning Models with the CICIoMT2024 Dataset

Abstract

The Internet of Medical Things (IoMT) has become integral to modern healthcare, enabling a wide range of applications from routine patient monitoring to critical medical interventions. While technological advancements have significantly enhanced the utility of IoMT, they have also increased its vulnerability to cyber attacks. This necessitates robust measures to protect users' privacy, confidentiality, and data availability in the healthcare sector. This study assessed the efficiency of using the models of machine and deep learning in classifying cybersecurity attacks within IoMT networks, utilizing the CICIoMT2024 dataset. The comparison included five architectures: XGBoost, Decision Tree (DT), Random Forest (RF), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). The results showed that the RF architecture surpassed the others in both accuracy and computational efficiency, reaching an accuracy rate of 99.83% for multi-class classification and 99.94% for binary classification.

Ähnliche Arbeiten