STAP Journal of Security Risk Management

ISSN: 3080-9444 (Online)

Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS

by 

Dena Abu Laila

PDF logoPDF

Published: 2025/10/02

Abstract

The proliferation of Internet of Things (IoT) devices in smart homes and industrial environments has created unprecedented security challenges, particularly regarding intrusion detection systems (IDS) susceptible to adversarial machine learning attacks. This paper presents a novel adversarial-aware defensive framework specifically designed for resource-constrained IoT environments, addressing the critical vulnerability of machine learning-based IDS to evasion attacks. Our lightweight protection mechanism integrates adversarial training techniques with computational efficiency optimizations, enabling real-time threat detection while maintaining robustness against sophisticated evasion attempts. The proposed framework employs a multi-layered defense strategy combining feature space transformations, ensemble-based detection, and adaptive threshold mechanisms to counter adversarial perturbations. Experimental evaluation on diverse IoT datasets demonstrates that our approach achieves 94.7% detection accuracy against clean traffic and maintains 89.3% effectiveness against state-of-the-art evasion attacks, while requiring only 15% additional computational overhead compared to traditional IDS. The framework’s adaptability to various IoT deployment scenarios and its ability to operate within stringent resource constraints make it particularly suitable for real-world implementation in smart infrastructure systems.

Keywords

Intrusion Detection System (IDS)Internet of Things (IoT)machine learning (ML)cybersecurity

Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS is licensed under CC BY 4.0CCBY

References

  1. A. Alsarhan, I. Al-Aiash, D. Al-Fraihat, M. Aljaidi, and D. A. A. H. A. Laila, "Expert phishing detection system," in Proceedings of the 2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), July 2024, pp. 54-59 https://doi.org/10.1109/IAICT62357.2024.10617460
  2. Al-Sarawi, Shadi, Mohammed Anbar, Kamal Alieyan, and Mahmood Alzubaidi. "Internet of Things (IoT) communication protocols." In 2017 8th International conference on information technology (ICIT), pp. 685-690. IEEE, 2017. https://doi.org/10.1109/ICITECH.2017.8079928.
  3. Khraisat, Ansam, Iqbal Gondal, Peter Vamplew, and Joarder Kamruzzaman. "Survey of intrusion detection systems: techniques, datasets and challenges." Cybersecurity 2, no. 1 (2019): 1-22. https://doi.org/10.1186/s42400-019-0038-7
  4. Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. "Explaining and harnessing adversarial examples." arXiv preprint arXiv:1412.6572 (2014).
  5. Butun, Ismail, Patrik Österberg, and Houbing Song. "Security of the Internet of Things: Vulnerabilities, attacks, and countermeasures." IEEE Communications Surveys & Tutorials 22, no. 1 (2019): 616-644. https://doi.org/10.1109/COMST.2019.2953364
  6. Madry, Aleksander, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. "Towards deep learning models resistant to adversarial attacks." arXiv preprint arXiv:1706.06083 (2017).
  7. Szegedy, Christian, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. "Intriguing properties of neural networks." arXiv preprint arXiv:1312.6199 (2013).
  8. Rigaki, Maria, and Sebastian Garcia. "Bringing a GAN to a knife-fight: Adapting malware communication to avoid detection." In 2018 IEEE Security and Privacy Workshops (SPW), pp. 70-75. IEEE, 2018. https://doi.org/10.1109/SPW.2018.00019
  9. Wang, Zheng. "Deep learning-based intrusion detection with adversaries." IEEE Access 6 (2018): 38367-38384. https://doi.org/10.1109/ACCESS.2018.2854599
  10. Hassija, Vikas, Vinay Chamola, Vikas Saxena, Divyansh Jain, Pranav Goyal, and Biplab Sikdar. "A survey on IoT security: application areas, security threats, and solution architectures." IEEe Access 7 (2019): 82721-82743. https://doi.org/10.1109/ACCESS.2019.2924045
  11. Meidan, Yair, Michael Bohadana, Yael Mathov, Yisroel Mirsky, Asaf Shabtai, Dominik Breitenbacher, and Yuval Elovici. "N-baiot-network-based detection of iot botnet attacks using deep autoencoders." IEEE Pervasive Computing 17, no. 3 (2018): 12-22
  12. Doshi, Rohan, Noah Apthorpe, and Nick Feamster. "Machine learning ddos detection for consumer internet of things devices." In 2018 IEEE security and privacy workshops (SPW), pp. 29-35. IEEE, 2018. https://doi.org/10.1109/SPW.2018.00013
  13. Anthi, Eirini, Lowri Williams, Małgorzata Słowińska, George Theodorakopoulos, and Pete Burnap. "A supervised intrusion detection system for smart home IoT devices." IEEE Internet of Things Journal 6, no. 5 (2019): 9042-9053. https://doi.org/10.1109/JIOT.2019.2926365
  14. Metzen, Jan Hendrik, Tim Genewein, Volker Fischer, and Bastian Bischoff. "On detecting adversarial perturbations." arXiv preprint arXiv:1702.04267 (2017).
  15. Li, Xin, and Fuxin Li. "Adversarial examples detection in deep networks with convolutional filter statistics." In Proceedings of the IEEE international conference on computer vision, pp. 5764-5772. 2017. https://doi.org/10.1109/ICCV.2017.615
  16. Dziugaite, Gintare Karolina, Zoubin Ghahramani, and Daniel M. Roy. "A study of the effect of jpg compression on adversarial images." arXiv preprint arXiv:1608.00853 (2016).