A Lightweight WDGP-1DCSP Model for High-Precision Intrusion Detection in Resource-Constrained IoT Edge Devices
DOI:
https://doi.org/10.54536/ajise.v5i1.7204Keywords:
Convolutional Neural Network, Cross-Stage Partial (CSP) Networks, Generative Adversarial Networks (GANs), Internet of Things (IoT), Intrusion Detection System (IDS), Lightweight Deep LearningAbstract
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.
Downloads
References
Akpaku, E., Chen, J., Ahmed, M., Sosu, R., Agbenyegah, F. K., & Louis, D. K. (2025). eBiTCN: Efficient bidirectional temporal convolution network for encrypted malicious network traffic detection. Journal of Computer Security, 33. https://doi.org/10.1177/0926227X251326282
Akpaku, E., Chen, J., Ahmed, M., Sosu, R. N. A., Agbenyegah, F. K., & Louis, D. K. (2025). eBiTCN: Efficient bidirectional temporal convolution network for encrypted malicious network traffic detection. Journal of Computer Security. https://doi.org/10.1177/0926227X251326282
Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. Sydney, NSW, Australia.
Booij, T. M., Chiscop, I., Meeuwissen, E., Moustafa, N., & den Hartog, F. T. H. (2022). ToN_IoT: The role of heterogeneity and the need for standardization of features and attack types in IoT network intrusion data sets. IEEE Internet of Things Journal, 9(1), 485-496. https://doi.org/10.1109/JIOT.2021.3082844
Chen, Z., Liu, J., Shen, Y., Simsek, M., Kantarci, B., Mouftah, H. T., & Djukic, P. (2022). Machine learning-enabled iot security: Open issues and challenges under advanced persistent threats. ACM Computing Surveys, 55(5), 1-35. https://doi.org/10.1145/3530812
Freitas de Araujo-Filho, P., Kaddoum, G., Campelo, D. R., Gondim Santos, A., Macedo, D., & Zerguine, A. (2021). Intrusion detection for cyber-physical systems using generative adversarial networks in fog environment. IEEE Internet of Things Journal, 8(8), 6247-6256. https://doi.org/10.1109/JIOT.2020.3028439
Goodfellow, I., Pouget-Abadie, J., & Mirza, M. (2014). Generative adversarial nets. Montreal, QC, Canada.
Gulrajani, I., Ahmed, F., & Arjovsky, M. (2017). Improved training of Wasserstein GANs. Long Beach, CA, USA.
Hadem, P., Saikia, D. K., & Moulik, S. (2021). An SDN-based intrusion detection system using SVM with selective logging for IP traceback. Computer Networks, 191, 108015. https://doi.org/10.1016/j.comnet.2021.108015
Hamidou, S. T., & Mehdi, A. (2025). Enhancing IDS performance through a comparative analysis of Random Forest, XGBoost, and Deep Neural Networks. Machine Learning with Applications, 22, 100738. https://doi.org/10.1016/j.mlwa.2025.100738
Hnamte, V., Hussain, J., & Saikia, L. C. (2025). A lightweight intrusion detection system using deep convolutional neural network. Computers & Electrical Engineering, 120, 109662. https://doi.org/10.1016/j.compeleceng.2025.109662
Howard, A., Sandler, M., & Chen, B. (2019). Searching for MobileNetV3. Seoul, South Korea.
Jiménez-López, D., Rodríguez-Barroso, N., Luzón, M. V., Del Ser, J., & Herrera, F. (2025). Membership inference attacks fueled by few-shot learning to detect privacy leakage and address data integrity. Machine Learning and Knowledge Extraction, 7(2), 43. https://doi.org/10.3390/make7020043
Khan, I. A., Moustafa, N., Pi, D., Sallam, K. M., Zomaya, A. A., & Li, Y. (2022). A new explainable deep learning framework for cyber threat discovery in industrial IoT networks. IEEE Internet of Things Journal, 9(13), 11604-11613. https://doi.org/10.1109/JIOT.2021.3124956
Kilincer, I. F., Ertam, F., & Sengur, A. (2021). Machine learning methods for cyber security intrusion detection: Datasets and comparative study. Computer Networks, 188, 107840. https://doi.org/10.1016/j.comnet.2021.107840
Li, Y. X., Zuo, Y., & Song, H. B. (2022). Deep learning in security of internet of things. IEEE Internet of Things Journal, 9(22), 22133-22146.
Misrak, S. F., & Ayele, T. W. (2025). Lightweight intrusion detection system for IoT with improved feature engineering and advanced dynamic quantization. Discover Internet of Things, 5(1), 1-25. https://doi.org/10.1007/s43926-025-00203-8
Muhammad, Z. (2026). Zero Trust Architecture (ZTA) Design and Implementation, A Comprehensive Review. American Journal of Innovation in Science and Engineering, 5, 18-25. https://doi.org/10.54536/ajise.v5i1.5905
Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. San Juan, Puerto Rico.
Sarhan, M., Layeghy, S., Moustafa, N., & Gallagher, M. (2024). Feature extraction for machine learning-based intrusion detection in IoT networks. Digital Communications and Networks, 10(2), 456-467. https://doi.org/10.1016/j.dcan.2022.07.003
Tolba, A., Nabil, N., & Sallam, K. (2024). Hybrid Deep Learning-Based Model for Intrusion Detection. Artificial Intelligence in Cybersecurity, (1) 2024. https://doi.org/10.61356/j.aics.2024.1198
Wang, C. Y., Liao, H. Y. M., & Wu, Y. H. (2020). CSPNet: A new backbone that can enhance learning capability of CNN. Seattle, WA, USA.
Wisanwanichthan, T., Thammarat, S., & Netisopakul, P. (2025). A Lightweight Intrusion Detection System for IoT and UAV Using Deep Neural Networks with Knowledge Distillation. Computers, 14(7), 291. https://doi.org/10.3390/computers14070291
Xiao, Y., Xing, C., Zhang, T., & Zhao, Z. (2019). An intrusion detection model based on feature reduction and convolutional neural networks. IEEE Access, 7, 42210-42219. https://doi.org/10.1109/ACCESS.2019.2904620
Zhang, H., Huang, L., Wu, C. Q., & Li, Z. (2020). An effective convolutional neural network based on SMOTE and Gaussian mixture model for intrusion detection in imbalanced dataset. Computer Networks, 177, 107315. https://doi.org/10.1016/j.comnet.2020.107315
Zhao, R., Gui, G., Xue, Z., Yin, J., Ohtsuki, T., Adebisi, B., & Gacanin, H. (2021). A Novel Intrusion Detection Method Based on Lightweight Neural Network for Internet of Things. IEEE Internet of Things Journal, 1-1. https://doi.org/10.1109/JIOT.2021.3119055
Zhao, Z., Li, Z., Jiang, J., Yu, F., Zhang, F., Xu, C., Zhao, X., Zhang, R., & Guo, S. (2023). ERNN: Error-resilient RNN for encrypted traffic detection towards network-induced phenomena. IEEE Transactions on Dependable and Secure Computing, 20(1), 1-15. https://doi.org/10.1109/TDSC.2022.3223603
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hani Iwidat
This work is licensed under a Creative Commons Attribution 4.0 International License.
