Home / Current Issue / Paper 1709463
Development and Testing of a Vulnerability Identification Model That Uses Deep Learning Model in A Healthcare IoT Architecture
Subject area: Science,Engineering and Technology · Area of research: Cybersecurity
Abstract
As a result of the speedy incorporation of Internet of Things (IoT) technologies in healthcare systems, it has managed to enhance service delivery, but also accelerated the appearance of potential cyber threats that jeopardize the safety of the patients, their data confidentiality, as well as the working dependability of the systems. This paper proposes the development and testing of a vulnerability identification model that uses deep learning model in a healthcare IoT setting. Three methods of deep neural networks (DNN) models, which comprise Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a combination of CNN+LSTM models, were trained and evaluated on real-life vulnerability data acquired at the University of Nigeria Teaching Hospital. Important performance vector was evaluated to test the models: loss, accuracy, precision, recall, and F1-score. The performance of CNN+LSTM hybrid model as evaluated revealed that it yielded the best result in all the metrics with an accuracy of 97 percent in training, 93 in validation, 94 percent precision, 95 percent recall and a f1-score of 94 percent. This would mean that there is better ability to identify and categorize vulnerabilities together with reduced false positives and anomalies. The conclusion points to the promise of hybrid deep learning methods in pursuing improved security in healthcare IoT systems in terms of real-time and reliable detection and response capabilities of threats.
Keywords
Healthcare; Internet of Things; Vulnerability; Deep Learning; CNN; LSTM
References
[1] Abdelrahman, M., Nguyen, T. L., Kharchouf, I., & Mohammed, O. (2023). A hybrid physical co- simulation smart grid testbed for testing and impact analysis of cyber-attacks on power systems: Framework and attack scenarios. Energies, 16 , 7771. https://
[2] Ashraf, I., Narra, M., Umer, M., Majeed, R., Sadiq, S., Javaid, F., & Rasool, N. (2022). A deep learning-based smart framework for cyber- physical and satellite system security threats detection. Electronics, 11(4), 667. https://
[3] Bernieri, G., Conti, M., & Pascucci, F. (2018). A novel architecture for cyber-physical security in industrial control networks. In 2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI) (pp. 1–6). IEEE. https://
[4] Iqbal, R., Doctor, F., More, B., Mahmud, S., & Yousuf, U. (2020). Big data analytics and computational intelligence for cyber-physical systems: Recent trends and state of the art applications. Future Generation Computer Systems, 105 , 766 –778. https://
[5] Khalid, A. R., Owoh, N., Uthmani, O., Ashawa, M., Osamor, J., &Adejoh, J. (2024). Enhancing CCF detection: An ensemble ML approach. Big Data and Cognitive Computing, 8(1), 6. https://
[6] Khan, S., Luo, F., Zhang, Z., Rahim, M. A., Ahmad, M., & Wu, K. (2022). Survey on issues and recent advances in vehicular public-key infrastructure (VPKI). IEEE Communications Surveys & Tutorials, 24, 1574–1601. https://
[7] Khazraei, A., Spencer, H., &Gao, Q. (2022). Learning-based vulnerability analysis of cyber- physical systems. In 2022 ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS) . https://
[8] Knowles, W., Prince, D., Hutchison, D., Disso, J., & Jones, K. (2015). A survey of cybersecurity management in industrial control systems. International Journal of Critical Infrastructure Protection, 9, 52–80. https://
[9] Markakis, E., Nikoloudakis, Y., Pallis, E., & Manso, M. (2019). Security assessment as a service cross-layered system for the adoption of digital, personalized, and trusted healthcare. In 2019 IEEE 5th World Forum on Internet of Things (WF -IoT) (pp. 91–94). https://
[10] Northern, B., Burks, T., Hatcher, M., Rogers, M., &Ulybyshev, D. (2021). VERCASM-CPS: Vulnerability analysis and cyber risk assessment for cyber-physical systems. Information, 12(10), 408. https://
[11] Parades, C. M., Martínez Castro, D., González Potes, A., Rey Piedrahita, A., & Ibarra Junquera, V. (2024). Design procedure for real- time cyber–physical systems tolerant to cyberattacks. Symmetry, 16(6), 684. https://
[12] Segovia-Ferreira, M., Rubio Hernan, J., Cavalli, A., &Garcia-Alfaro, J. (2023). Cyber-resilience approaches for cyber-physical systems. arXiv. https://arxiv.org/abs/2302.05402
[13] Umer, M., Sadiq, S., Karamti, H., Alhebshi, R. M., Alnowaiser, K., Eshmawi, A. A., Song, H., & Ashraf, I. (2022). Deep learning-based intrusion detection methods in cyber-physical systems: Challenges and future trends. Electronics, 11 (20), 3326. https://
[14] Vyas, S., & Bhargava, D. (2021). Cyber- physical systems for healthcare. In Smart Health Systems (pp. [chapter pages, if available]). Springer, Singapore. https://
[15] Wang, Y., Zhao, Z., Qi, B., Cheng, Y., Tang, K., & Li, B. (2024). Vulnerability analysis of an electric vehicle fleet for car-sharing service under cyber attacks. Sustainable Energy, Grids and Networks, 37 , 101207. https://
[16] Xu, J., Xue, K., Li, S., Tian, H., Hong, J., Hong, P., & Yu, N. (2019). Healthchain: A blockchain-based privacy preserving scheme for large-scale health data. IEEE Internet of Things Journal, 6 (5), 8770 –8781. https://
[17] Yuan, S., Yang, M., & Reniers, G. (2024). Integrated process safety and process security risk assessment of industrial cyber-physical systems in chemical plants. Computers in Industry, 155 , 104056. https://
[18] Zhou, F. Y., Jin, L. P., & Dong, J. (2017). Review of convolutional neural network. Chinese Journal of Computers, 40, 1229–1251.
How to cite this paper
@article{1709463,
author = {Mba Chioma Juliet, Ozioko Ekene Frank, Ezugwu Lilian Martina},
title = {Development and Testing of a Vulnerability Identification Model That Uses Deep Learning Model in A Healthcare IoT Architecture},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {1},
pages = {10-20},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1709463.pdf},
abstract = {As a result of the speedy incorporation of Internet of Things (IoT) technologies in healthcare systems, it has managed to enhance service delivery, but also accelerated the appearance of potential cyber threats that jeopardize the safety of the patients, their data confidentiality, as well as the working dependability of the systems. This paper proposes the development and testing of a vulnerability identification model that uses deep learning model in a healthcare IoT setting. Three methods of deep neural networks (DNN) models, which comprise Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a combination of CNN+LSTM models, were trained and evaluated on real-life vulnerability data acquired at the University of Nigeria Teaching Hospital. Important performance vector was evaluated to test the models: loss, accuracy, precision, recall, and F1-score. The performance of CNN+LSTM hybrid model as evaluated revealed that it yielded the best result in all the metrics with an accuracy of 97 percent in training, 93 in validation, 94 percent precision, 95 percent recall and a f1-score of 94 percent. This would mean that there is better ability to identify and categorize vulnerabilities together with reduced false positives and anomalies. The conclusion points to the promise of hybrid deep learning methods in pursuing improved security in healthcare IoT systems in terms of real-time and reliable detection and response capabilities of threats.},
keywords = {Healthcare; Internet of Things; Vulnerability; Deep Learning; CNN; LSTM},
month = {July},
}