A Lightweight WDGP-1DCSP Model for High-Precision Intrusion Detection in Resource-Constrained IoT Edge Devices
American Journal of Innovation in Science and Engineering · 18.03.2026 · 5 (1) · 74-85
DOI: 10.54536/ajise.v5i1.7204 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Innovation in Science and Engineering, online erschienen am 18.03.2026. Verfasst von Hani Iwidat. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
As technology advances, network intrusion techniques are diversifying, presenting significant security challenges for resource-constrained edge devices in IoT environments. Addressing the generally poor detection performance and unsuitability of traditional intrusion detection models for edge devices in the current IoT environment, which suffer from limited resources and low computing power, this paper proposes a lightweight model based on Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNNs) for detecting intrusion behavior in the IoT environment. Firstly, GAN technology is used to solve the data imbalance problem. Secondly, a lightweight CNN with a cross-stage local structure is used to extract traffic features, and H-swish is selected as the activation function to reduce computational load and improve computational efficiency. Finally, Softmax is used to classify the traffic data. Experimental results on the TON_IOT and CICIDS2018 datasets demonstrate the model’s exceptional performance. The proposed model achieved accuracy rates of 99.52% and 99.53%, precision rates of 99.41% and 99.28%, recall rates of 99.57% and 99.52%, and F1-scores of 99.44% and 99.37% on the TON_IOT and CICIDS2018 datasets, respectively. The model size is limited to 21-32 KB. These results demonstrate that the proposed model, while maintaining intrusion detection accuracy, reduces model size and computational load, thereby meeting the high-precision intrusion detection requirements of demanding IoT environments.
Zitieren
APA
Iwidat, H. (2026). A Lightweight WDGP-1DCSP Model for High-Precision Intrusion Detection in Resource-Constrained IoT Edge Devices. American Journal of Innovation in Science and Engineering, 5(1), 74-85. https://doi.org/10.54536/ajise.v5i1.7204
Vancouver
Iwidat H. A Lightweight WDGP-1DCSP Model for High-Precision Intrusion Detection in Resource-Constrained IoT Edge Devices. American Journal of Innovation in Science and Engineering. 2026;5(1):74-85. doi:10.54536/ajise.v5i1.7204
BibTeX
@article{Iwidat2026,
author = {Iwidat, Hani},
title = {A Lightweight WDGP-1DCSP Model for High-Precision Intrusion Detection in Resource-Constrained IoT Edge Devices},
journal = {American Journal of Innovation in Science and Engineering},
year = {2026},
volume = {5},
number = {1},
pages = {74--85},
doi = {10.54536/ajise.v5i1.7204}
}
EUVIMED