Comparative Evaluation of Transformer, GNN, and Reinforcement Learning Models for Intrusion Detection in Internet of Medical Things
A N Naralasetty Nikhila1, Dharmaiah Devarapalli2
1A N Naralasetty Nikhila, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation (KLEF), Guntur (Andhra Pradesh), India.
2Dr. Dharmaiah Devarapalli, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation (KLEF), Guntur (Andhra Pradesh), India.
Manuscript received on 05 December 2025 | First Revised Manuscript received on 15 December 2025 | Second Revised Manuscript received on 29 December 2025 | Manuscript Accepted on 15 January 2026 | Manuscript published on 30 January 2026 | PP: 1-11 | Volume-15 Issue-2, January 2026 | Retrieval Number: 100.1/ijitee.B120815020126 | DOI: 10.35940/ijitee.B1208.15020126
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The increasing prevalence of cyber threats across Internet of Medical Things (IoMT) ecosystems poses critical challenges for safeguarding patient safety and data integrity, necessitating a dynamic, resilient intrusion detection system (IDS). In this work, we present a comprehensive machine learning framework for classifying cyberattacks in IoMT settings using biometric and network traffic data from the publicly available WUSTL-EHMS-2020 dataset. We conduct a unique comparative analysis using three paradigms: a Graph Neural Network (GNN) model to capture structural dependencies; a Transformer deep learning model to capture contextual relationships; and a lightweight baseline classifier, Logistic Regression. We undertook extensive data preparation, including label encoding, normalisation, and stratified sampling to maintain class balance. The Transformer achieved the highest overall classification accuracy in the IoMT ecosystem (93.5%), outperforming both GNN (88.7%) and Logistic Regression (92.8%) across all evaluation metrics. Our research demonstrates the superior ability of attention-based models to identify complex threat patterns in heterogeneous IoMT data. Our study provides a reproducible benchmarking framework and lays the groundwork for future efforts related to hybrid modelling, explainable AI, and federated learning to improve the cybersecurity of Smart Healthcare Systems.
Keywords: Internet of Medical Things, Cybersecurity, Intrusion Detection, Medical Cyber Physical Systems, Anomaly Detection.
Scope of the Article: Artificial Intelligence & Methods