Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS
STAP Journal of Security Risk Management · 2025
DOI: 10.63180/jsrm.thestap.2025.1.3 ↗Kurz gefasst
Fachartikel in der Zeitschrift STAP Journal of Security Risk Management, 2025. Verfasst von Dena Abu Laila. Die Arbeit wurde bisher 17-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Laila, D. A. (2025). Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS. STAP Journal of Security Risk Management. https://doi.org/10.63180/jsrm.thestap.2025.1.3
Vancouver
Laila DA. Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS. STAP Journal of Security Risk Management. 2025. doi:10.63180/jsrm.thestap.2025.1.3
BibTeX
@article{Laila2025,
author = {Laila, Dena Abu},
title = {Responsive Machine Learning Framework and Lightweight Utensil of Prevention of Evasion Attacks in the IoT-Based IDS},
journal = {STAP Journal of Security Risk Management},
year = {2025},
doi = {10.63180/jsrm.thestap.2025.1.3}
}
EUVIMED