AI-Based Intrusion Detection in IoT Networks Using Lightweight Deep Learning Models

International Journal of Emerging Research in Science, Engineering, and Management

Vol. 1, Issue 4, pp. 01–08, October 2025

https://doi.org/10.58482/ijersem.v1i4.1

This work is licensed under a Creative Commons Attribution 4.0 International License .

AI-Based Intrusion Detection in IoT Networks Using Lightweight Deep Learning Models

Sujilatha T, V Mamatha

Assistant Professor, Department of CSE, N.B.K.R. Institute of Science and Technology, Vidyanagar, India.

Abstract

The exponential growth of the Internet of Things (IoT) ecosystem has revolutionised automation and connectivity across diverse domains, but it has also amplified cybersecurity vulnerabilities due to the heterogeneous, large-scale, and resource-constrained nature of IoT devices. Traditional intrusion detection systems (IDS) struggle to achieve scalability, low latency, and real-time adaptability in such dynamic environments. This paper proposes a lightweight deep learning-based intrusion detection framework tailored for IoT networks, emphasising computational efficiency, high detection accuracy, and Model interpretability. The proposed architecture integrates optimised convolutional and recurrent modules with attention mechanisms for effective spatial–temporal feature extraction while maintaining a minimal parameter count, making it suitable for deployment on edge and embedded devices. Unlike conventional heavy models such as OSEN-IoT and CST-AFNet, the proposed framework balances accuracy and efficiency by leveraging reduced-parameter neural blocks inspired by Kolmogorov–Arnold Networks (TFKAN) and TinyML optimisation strategies. Extensive evaluation on benchmark datasets, including BoT-IoT, ToN-IoT, and CICIoT2023, demonstrates that the proposed model achieves detection accuracy exceeding 99%, with a false positive rate below 0.2%, outperforming existing approaches such as CAEAID, Ex3WNN, and FedMSE while reducing computational overhead by more than 65%. This research contributes to the development of scalable, interpretable, and lightweight intrusion detection systems capable of securing large-scale IoT deployments in real time.

Keywords: IoT Security, Intrusion Detection System (IDS), Lightweight Deep Learning, Edge Computing, TinyML.

📄 Download Full Text PDF

DOI: https://doi.org/10.58482/ijersem.v1i4.1

Open Access • Peer Reviewed Article

References

  1. S. Ullah, J. Wu, M. M. Kamal, H. G. Mohamed, M. Sheraz, and T. C. Chuah, “MBID: A Scalable Multi-Tier Blockchain Architecture with Physics-Informed Neural Networks for Intrusion Detection in Large-Scale IoT Networks,” Computer Modeling in Engineering & Sciences, vol. 0, no. 0, pp. 1–10, Jan. 2025. https://doi.org/10.32604/cmes.2025.068849
  2. W. Ishtiaq, A. Zannat, A. H. M. S. Parvez, Md. A. Hossain, M. H. Kanchan, and M. M. Tarek, “CST-AFNET: A Dual Attention-Based Deep Learning Framework for Intrusion Detection in IoT Networks,” Array, vol. 27, p. 100501, Aug. 2025. https://doi.org/10.1016/j.array.2025.100501
  3. M. M. Rahman, S. A. Shakil, and M. R. Mustakim, “A Survey on Intrusion Detection System in IoT Networks,” Cyber Security and Applications, vol. 3, p. 100082, Dec. 2024. https://doi.org/10.1016/j.csa.2024.100082
  4. S. Asif, “OSEN-IoT: An Optimized Stack Ensemble Network with Genetic Algorithm for Robust Intrusion Detection in Heterogeneous IoT Networks,” Expert Systems with Applications, p. 127183, Mar. 2025. https://doi.org/10.1016/j.eswa.2025.127183
  5. A. Idri and A. Hamdouchi, “Evaluating the Performance of TinyML Singular and Ensemble Techniques for Intrusion Detection in IoT Networks,” Microprocessors and Microsystems, p. 105172, Jun. 2025. https://doi.org/10.1016/j.micpro.2025.105172
  6. I. A. Fares, M. A. Elaziz, A. O. Aseeri, H. S. Zied, and A. G. Abdellatif, “TFKAN: Transformer Based on Kolmogorov–Arnold Networks for Intrusion Detection in IoT Environment,” Egyptian Informatics Journal, vol. 30, p. 100666, Apr. 2025. https://doi.org/10.1016/j.eij.2025.100666
  7. F. Wahab, S. Ma, Y. Zhao, and A. Shah, “An Explainable Three-Way Neural Network Approach for Intrusion Detection in IoT Ecosystem,” Internet of Things, p. 101722, Aug. 2025. https://doi.org/10.1016/j.iot.2025.101722
  8. F. Cerasuolo, G. Bovenzi, D. Ciuonzo, and A. Pescapè, “Attack-Adaptive Network Intrusion Detection Systems for IoT Networks Through Class Incremental Learning,” Computer Networks, p. 111228, Mar. 2025. https://doi.org/10.1016/j.comnet.2025.111228
  9. V. T. Nguyen and R. Beuran, “FedMSE: Semi-Supervised Federated Learning Approach for IoT Network Intrusion Detection,” Computers & Security, p. 104337, Jan. 2025. https://doi.org/10.1016/j.cose.2025.104337
  10. Z. Yin, H. Chen, H. Ma, T. Hu, and L. Bai, “CAEAID: An Incremental Contrast Learning-Based Intrusion Detection Framework for IoT Networks,” Computer Networks, p. 111161, Mar. 2025. https://doi.org/10.1016/j.comnet.2025.111161
  11. A. K. Silivery, K. R. M. Rao, and R. Solleti, “Dual-Path Feature Extraction Based Hybrid Intrusion Detection in IoT Networks,” Computers & Electrical Engineering, vol. 122, p. 109949, Dec. 2024. https://doi.org/10.1016/j.compeleceng.2024.109949
  12. A. Pasam, A. Sinha, and A. Mailewa, “Lightweight AI-Based Intrusion Detection Models for IoT Devices: A Comparative Review,” 2025 IEEE International Carnahan Conference on Security Technology (ICCST), San Antonio, TX, USA, 2025, pp. 1–7. https://doi.org/10.1109/ICCST63435.2025.11295730
Download PDF

This article is part of Volume 1, Issue 4 (October 2025)

2025-10-31