Development of A Machine Learning-Based Security Module for ‎Detecting Exploit-Type Attacks in IoT Networks

  • Authors

    • P Bavithra Matharasi Department of Computer Science (MCA), Mount Carmel College, Autonomous, Bengaluru, Karnataka 560052, India
    • M Chennakesavulu Department of Electronics and Communication Engineering, Rajeev Gandhi Memorial College of Engineering and Technology (Autono-‎mous), Nandyal, Andhra Pradesh 518501, India
    • Manjula Prabakaran S Department of Computer Science and Engineering (Data Science)، Madanapalle Institute of Technology & Science, Madanapalle, Andhra ‎Pradesh 517325, India
    • Dheeraj Akula Department of North America Applications, Oracle Corporation, Austin, Texas 78741, USA
    • S. Lakshminarasimhan Department of Artificial Intelligence and Data Science, J.J. College of Engineering and Technology, Tiruchirappalli, Tamil Nadu 620009, ‎India
    • Ravindra Namdeorao Jogekar Department of Computer Science and Engineering, Jhulelal Institute of Technology, Nagpur, Maharashtra 441111, India
    • Naveen Mukkapati Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh 522502, ‎India
    • Tatiraju.V.Rajani Kanth TVR Consulting Services Private Limited, Hyderabad, Telangana 500055, India
    https://doi.org/10.14419/6m5nbj91

    Received date: June 9, 2025

    Accepted date: July 19, 2025

    Published date: July 25, 2025

  • Machine Learning; IoT Networks; Security Module; Exploit-Type Attacks

  • Abstract

    This study investigated the effectiveness of a two-layer neural network (NN) model in detecting malicious-based cyberattacks. The model ‎showed strong classification performance with 0.92 precision, 0.965 recall, and F1 score of 0.92. The SMOTE (Synthetic Minority Over-sampling Technique) method was used to solve the class imbalance problem, which greatly improved the prediction ability of the model. In ‎addition, OneHotEncoding was used to convert categorical variables into binary format, which further improved the accuracy of the model. ‎The results demonstrate the potential of deep learning methods, especially NNs, for cybersecurity tasks, demonstrating their ability to accurately detect complex and deep patterns of malicious usage‎.

  • References

    1. Alosaimi, S., & Almutairi, S. M. (2023). An intrusion detection system using BoT-IoT. Applied Sciences, 13(9), 5427. https://doi.org/10.3390/app13095427.
    2. Damaševičius, R., Bacanin, N., & Misra, S. (2023). From sensors to safety: Internet of Emergency Services (IoES) for emergency response and dis-aster management. Journal of Sensor and Actuator Networks, 12, 41. https://doi.org/10.3390/jsan12030041.
    3. Yogesh, K. M., Stephan, T., Bharath, M. B., Gad, I., Arpitha, S., & Prakash, M. M. (2023). Characterization of darknet traffic detection using time domain features. In Proceedings of the International Conference on Computer Vision and Internet of Things (ICCVIoT’T) (pp. 233–237). https://doi.org/10.1049/icp.2023.2881.
    4. Alotaibi, B. (2023). A survey on industrial Internet of Things security: Requirements, attacks, AI-based solutions, and edge computing opportuni-ties. Sensors, 23, 7470. https://doi.org/10.3390/s23177470.
    5. Srinivasan, S., & Deepalakshmi, P. (2023). Enhancing the security in cyberworld by detecting the botnets using ensemble classification based ma-chine learning. Measurement: Sensors, 25, 100624. https://doi.org/10.1016/j.measen.2022.100624.
    6. Ju, Z., Zhang, H., Li, X., Chen, X., Han, J., & Yang, M. (2022). A survey on attack detection and resilience for connected and automated vehicles: From vehicle dynamics and control perspective. IEEE Transactions on Intelligent Vehicles, 7, 815–837. https://doi.org/10.1109/TIV.2022.3186897.
    7. Bahashwan, A. A., Anbar, M., Manickam, S., Al-Amiedy, T. A., Aladaileh, M. A., & Hasbullah, I. H. (2023). A systematic literature review on ma-chine learning and deep learning approaches for detecting DDoS attacks in software-defined networking. Sensors, 23(9), 4441. https://doi.org/10.3390/s23094441.
    8. Alam, S., Bhatia, S., Shuaib, M., Khubrani, M. M., Alfayez, F., Malibari, A. A., & Ahmad, S. (2023). An overview of blockchain and IoT integra-tion for secure and reliable health records monitoring. Sustainability, 15, 5660. https://doi.org/10.3390/su15075660.
    9. Rihan, S. D. A., Anbar, M., & Alabsi, B. A. (2023). Approach for detecting attacks on IoT networks based on ensemble feature selection and deep learning models. Sensors, 23(17), 7342. https://doi.org/10.3390/s23177342.
    10. Suleski, T., Ahmed, M., Yang, W., & Wang, E. (2023). A review of multi-factor authentication in the Internet of Healthcare Things. Digital Health, 9, https://doi.org/10.1177/20552076231177144.
    11. Al-Amiedy, T. A., Anbar, M., Belaton, B., Bahashwan, A. A., Hasbullah, I. H., Aladaileh, M. A., & Mukhaini, G. A. (2023). A systematic litera-ture review on attacks defense mechanisms in RPL-based 6LoWPAN of Internet of Things. Internet of Things, 22, 100741. https://doi.org/10.1016/j.iot.2023.100741.
    12. Sodhro, A. H., Awad, A. I., van de Beek, J., & Nikolakopoulos, G. (2022). Intelligent authentication of 5G healthcare devices: A survey. Internet of Things, 20, 100610. https://doi.org/10.1016/j.iot.2022.100610.
    13. Nova, K. (2022). Security and resilience in sustainable smart cities through cyber threat intelligence. International Journal of Information and Cy-bersecurity, 6, 21–42.
    14. Elattar, M., Younes, A., Gad, I., & Elkabani, I. (2024). Explainable AI model for PDFMal detection based on gradient boosting model. Neural Computing and Applications, 36(34), 21607–21622. https://doi.org/10.1007/s00521-024-10314-y.
    15. Wei, C., Xie, G., & Diao, Z. (2023). A lightweight deep learning framework for botnet detecting at the IoT edge. Computers & Security, 129, 103195. https://doi.org/10.1016/j.cose.2023.103195.
    16. Salunkhe, V., Tangudu, A., Mokkapati, C., Goel, D. P., & Aggarwal, A. (2024). Advanced encryption techniques in healthcare IoT: Securing pa-tient data in connected medical devices. Modern Dynamics in Mathematics and Progressions, 1, 224–247. https://doi.org/10.36676/mdmp.v1.i2.22.
    17. Alkadi, S., Al-Ahmadi, S., & Ben Ismail, M. M. (2024). RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic. Sensors, 24, 2626. https://doi.org/10.3390/s24082626.

  • Downloads

  • How to Cite

    Matharasi, P. B. ., Chennakesavulu, M. ., S, M. P., Akula , D. ., Lakshminarasimhan , S. ., Jogekar, R. N. ., Mukkapati, N. ., & Kanth, T. . (2025). Development of A Machine Learning-Based Security Module for ‎Detecting Exploit-Type Attacks in IoT Networks. International Journal of Basic and Applied Sciences, 14(3), 286-297. https://doi.org/10.14419/6m5nbj91