A Hybrid CNN-BiLSTM Based Cyberattack Detection Framework for IoMT and 6G Healthcare Environments

The rapid expansion of the Internet of Medical Things (IoMT) has significantly enhanced healthcare systems but has also exposed them to sophisticated cyber threats. With the advent of 6G healthcare ecosystems, these challenges become even more critical due to ultra-dense connectivity and massive data exchange. Existing security mechanisms often fall short due to the heterogeneous nature of IoMT networks. In this work, we propose a hybrid model-based Intrusion Detection System (IDS) to secure IoMT environments. The proposed model is built using a 1D-CNN-BiLSTM architecture to accurately detect anomalies by capturing spatial patterns and temporal dependencies in network traffic. Experimental evaluations are performed on the ECU-IoHT dataset. Results demonstrate that the proposed system outperforms existing methods and achieves an accuracy of 99.40%, an F1-score of 98.95%, and a ROC-AUC score of 99.87%. These results affirm the superiority of the proposed IDS and highlight its potential as a robust security solution for safeguarding 6G healthcare-driven IoMT infrastructures.