Modeling of Transformer-Based Autoencoder Architecture for Secure IoT-Based Intrusion Detection in Critical Healthcare Systems
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 January 2026
,
Page 1-7
https://doi.org/10.22037/ijmtfm.v16.53130
Abstract
Background: The Internet of Things (IoT) is widely used in healthcare for patient monitoring and continuous data collection. In intensive care unit (ICU) environments, many connected medical devices are used to monitor patient conditions in real time. Existing intrusion detection approaches using machine learning (ML) and deep learning (DL) have shown good results, but many still struggle with high-dimensional, complex network traffic data. Therefore, a more effective intrusion detection approach is required for secure IoT-based healthcare systems. The model is designed to distinguish between normal and malicious traffic in healthcare systems using deep learning approaches.
Methods: In the proposed model, relevant features are selected using a statistical and information-theoretic approach based on mutual information, variance thresholding, and correlation analysis to remove redundant information. For classification, a transformer-based autoencoder learns meaningful representations from network traffic, and a multilayer perceptron classifies the representations into normal and malicious classes. To improve model performance, Bayesian Optimization is leveraged for hyperparameter tuning.
Results: The proposed TAE-SHID model was evaluated using a benchmark dataset. The model achieved an accuracy of 96.86%, showing good classification performance compared with existing methods.
Conclusion: The results show that the proposed TAE-SHID model is effective for classification and outperforms existing methods.
- Internet of Things
- Healthcare Security
- Intrusion Detection System
- Transformer-Based Autoencoder
- Intensive Care Unit
- Bayesian Optimization
How to Cite
References
[1] Hezam M, Ismail MM, Ali AM, Sallam K, Abdel-Basset M. DP-DL-ZT: a zero-trust-enhanced differential privacy framework with CNN-LSTM for cyber threat detection in IoT healthcare. Neural Comput Appl. 2026;38(8):289. [DOI: 10.1007/s00521-026-11890-x]
[2] Priyadarshani PP, Nayak J, Dash PB. Optimizer influenced deep neural network for IoT healthcare security. SN Comput Sci. 2026;7(1):118. [DOI: 10.1007/s42979-025-04657-z]
[3] Alfakeeh S. A blockchain-enabled IoT framework for secure attack detection and advanced feature selection in smart healthcare. Eng Technol Appl Sci Res. 2025;15(5):28219-23. [DOI: 10.48084/etasr.13349]
[4] Ali TE, Zoltan AD. Hierarchical deep learning for robust cybersecurity in multi-cloud healthcare infrastructures. Eng Technol Appl Sci Res. 2025;15(1):20358-66. [DOI: 10.48084/etasr.8918]
[5] Musthafa S, Jenifa G, Murugan L, Moorthy U. IoT based security enhanced continuous health monitoring framework using lightweight cryptography and deep learning techniques. Int J Comput Intell Syst. 2026. [DOI: 10.1007/s44196-026-01237-8]
[6] Kateb F, Ragab M, Abukhodair F, Abdulkader OA, Maghrabi LA, Binyamin SS, et al. Improved security for IoT-based remote healthcare systems using deep learning with jellyfish search optimization algorithm. Sci Rep. 2025;15(1):13223. [DOI: 10.1038/s41598-025-97065-5]
[7] Naik N, Surendranath N, Raju SAB, Madduri C, Dasari N, Shukla VK, et al. Hybrid deep learning-enabled framework for enhancing security, data integrity, and operational performance in Healthcare Internet of Things (H-IoT) environments. Sci Rep. 2025;15(1):31039. [DOI: 10.1038/s41598-025-15292-2]
[8] Arthi R, Krishnaveni S, Zeadally S. An intelligent SDN-IoT enabled intrusion detection system for healthcare systems using a hybrid deep learning and machine learning approach. China Commun. 2024;21(10):1-21. [DOI: 10.23919/JCC.ja.2022-0681]
[9] Mohammadi H, Ghahramani S, Asghari SA, Aminian M. Securing healthcare with deep learning: a CNN-based model for medical IoT threat detection. In: 2024 19th Iranian Conference on Intelligent Systems (ICIS). IEEE; 2024. p. 168-73. [DOI: 10.1109/ICIS64839.2024.10887510]
[10] Kumar PM, Kavin BP, Jagathpally A, Shahwar T. Transforming the cybersecurity space of healthcare IoT devices using deep learning. In: 2025 IEEE 4th International Conference on AI in Cybersecurity (ICAIC). IEEE; 2025. p. 1-6. [DOI: 10.1109/ICAIC63015.2025.10849305]
[11] Das D, Ghosh U, Shetty S, Mohanty S. Machine learning-enabled IoT applications for smart healthcare monitoring systems. Adv Comput. 2025;137:175-218. [DOI: 10.1016/bs.adcom.2024.06.007]
[12] García S, Ramírez-Gallego S, Luengo J, Benítez JM, Herrera F. Big data preprocessing: methods and prospects. Big Data Anal. 2016;1(1):9. [DOI: 10.1186/s41044-016-0014-0]
[13] Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157-82. [Link]
[14] Graves A, Mohamed AR, Hinton G. Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE; 2013. p. 6645-7. [DOI: 10.1109/ICASSP.2013.6638947]
[15] Snoek J, Larochelle H, Adams RP. Practical Bayesian optimization of machine learning algorithms. Adv Neural Inf Process Syst. 2012;25.
[16] Faisal Malik. IoT healthcare security dataset [Internet]. Kaggle. [Link]
[17] Darwish R, Abdelsalam M, Khorsandroo S. Deep learning-based XIoT malware analysis: a comprehensive survey, taxonomy, and research challenges. J Netw Comput Appl. 2025;242:104258. [DOI: 10.1016/j.jnca.2025.104258]
[18] Khan SH, Alahmadi TJ, Ullah W, Iqbal J, Rahim A, Alkahtani HK, et al. A new deep boosted CNN and ensemble learning based IoT malware detection. Comput Secur. 2023;133:103385. [DOI: 10.1016/j.cose.2023.103385]
[19] Hossain MA. Deep learning-based intrusion detection for IoT networks: a scalable and efficient approach. EURASIP J Inf Secur. 2025;2025(1):28. [DOI: 10.1186/s13635-025-00202-w]
- Abstract Viewed: 7 times
- PDF Downloaded: 9 times