Explainable Quantum Convolutional Neural Network for Attack Detection in Healthcare IoMT Systems Using SHAP and Grid5000 Computing

The growth of the Internet of Medical Things (IoMT) improves patient care and data analysis, but it alsomakes healthcare systems newly vulnerable to cyberattacks.Current intrusion detection systems (IDS) strug-gle to work with the many different IoMT protocols. More importantly, they are ”black boxes” that can’texplain their decisions, which is a major problem in healthcare where safety is critical. This paper pro-poses a hybrid explainable quantum convolutional neural network (QCNN–SHAP) framework for accurateand transparent attack detection in IoMT environments. The QCNN exploits quantum feature encoding andentanglement to capture complex correlations in high-dimensional IoMT traffic data, while SHAP (SHapleyAdditive exPlanations) provides feature-level interpretability for each detection decision. We tested our modelon the CICIoMT2024 dataset, a benchmark for multi-protocol IoMT security assessment, using the Grid5000distributed computing platform. The proposed QCNN–SHAP model achieved a detection accuracy of 98.05%,outperforming current models like CNN, LSTM–Autoencoder, and Transformer–XAI models while maintain-ing explainability and moderate computational cost. SHAP analysis showed that key network features suchas packet size variance, flow duration, and protocol type were the most influential in identifying attacks. Theresults validate the model’s robustness, interpretability, and suitability for real-time IoMT intrusion detectionin healthcare contexts.