An Intrusion Detection System For Detecting DDoS Attacks In Blockchain-Enabled IoMT Networks

The integration of blockchain technology with the Internet of Medical Things (IoMT) has become a cornerstone of modern healthcare, facilitating a wide range of applications from routine patient monitoring to critical medical interventions. Despite the enhanced security that blockchain offers to IoMT systems, these networks remain vulnerable to various cyber threats, particularly Distributed Denial of Service (DDoS) attacks. Such attacks are designed to disrupt services, hindering legitimate users from accessing the network and conducting essential transactions. Consequently, there is a pressing need for robust strategies to safeguard the availability and resilience of healthcare systems. This study introduces a novel Machine Learning (ML) Intrusion Detection System (IDS) designed to mitigate DDoS attacks in blockchain-enabled IoMT networks (BIoMT), employing the most recent CICIoMT2024 dataset. The system encompasses three models: XGBoost, Decision Tree (DT), and Random Forest (RF). The results demonstrate that all models achieve high performance across metrics such as accuracy, precision, recall, and F1-score. However, in terms of prediction time, the DT model emerges as the most efficient, offering the lowest time cost for predictions.