JNACSISSN:2582-3817

JS-DKN: Jensen Shannon with Deep Kronecker Networks for Feature Fusion in IoT Intrusion Detection

  • Shanoor Afreen

Abstract

Intrusion detection is considered the process of examining or monitoring traffic in the network, user behavior, and system function, to recognize the unofficial anomalous or access actions that could indicate the cyberattacks or security breaches. In intrusion detection, unifying multiple features causes redundancy, and irreverent features are added and causing a waste of computational resources. Thus, this research presented a new technique named Jensen Shannon Deep Kronecker Networks with Deep Stacked Autoencoders (JS-DKN +DSA) for feature fusion in IoT intrusion detection. At first, the simulation of IoT is performed, and thereafter, the input network traffic data is applied to data normalization. Furthermore, the z-score is utilized for data normalization to improve the quality of data. Thereafter, feature fusion is performed by the Jensen Shannon with Deep Kronecker Networks (JS-DKN), in which the JS is employed to find the relevant features, and the DKN is applied to find the fusion coefficient. Lastly, intrusion detection in IoT is effectuated by the Deep Stacked Autoencoder (DSA) and produces output as attack or normal. In addition, the presented JS-DKN +DSA approach recorded the highest accuracy of 90.876%, True Negative Rate (TNR) of 88.654%, and a True Positive Rate (TPR) of 92.766 %.

References

  • A. Awajan, “A novel deep learning-based intrusion detection system for IOT networks”, Computers, vol,12, no.2, pp.34, 2023.
  • S. Baniasadi, O. Rostami, D. Martín, and M. Kaveh, “A novel deep supervised learning-based approach for intrusion detection in IoT systems”, Sensors, vol.22, no. 12, pp.4459, 2022.
  • K. H. Le, M. H. Nguyen, T. D. Tran, and N. D. Tran, “IMIDS: An intelligent intrusion detection system against cyber threats in IoT”, Electronics, vol.11, no.4, pp.524, 2022.
  • J. A. Faysal, S. T. Mostafa, J. S. Tamanna, K. M. Mumenin, M. M. Arifin, M. A. Awal, A. Shome, and S. S. Mostafa, “XGB-RF: A hybrid machine learning approach for IoT intrusion detection”, In Telecom, Vol. 3, No. 1, pp. 52-69, January, MDPI, 2022.
  • K. Albulayhi, Q. Abu Al-Haija, S. A. Alsuhibany, A. A. Jillepalli, M. Ashrafuzzaman, and F. T. Sheldon, “IoT intrusion detection using machine learning with a novel high performing feature selection method”, Applied Sciences, vol.12, no.10, pp.5015, 2022.
  • M. Zhong, Y. Zhou, and G. Chen, “Sequential model-based intrusion detection system for IoT servers using deep learning methods”, Sensors, vol.21, no.4, pp.1113, 2021.
  • M. Z. Al-Faiz, A. A. Ibrahim, and S. M. Hadi, “The effect of Z-Score standardization (normalization) on binary input due the speed of learning in back-propagation neural network”, Iraqi Journal of Information and Communication Technology, vol.1, no.3, pp.42-48 b, 2018.
  • L. Feng, and G. Yang, “Deep Kronecker Network”, arXiv preprint arXiv:2210.13327, 2022.
  • Y. Yu, J. Li, J. Li, Y. Xia, Z. Ding, and B. Samali, “Automated damage diagnosis of concrete jack arch beam using optimized deep stacked autoencoders and multi-sensor fusion”, Developments in the Built Environment, vol.14, pp.100128, 2023.
  • O. Elnakib, E. Shaaban, M. Mahmoud, and K. Emara, “EIDM: deep learning model for IoT intrusion detection systems”, The Journal of Supercomputing, vol.79, no. 12, pp.13241-13261, 2023.
  • S. Hajj, J. Azar, J. Bou Abdo, J. Demerjian, C. Guyeux, A. Makhoul, and D. Ginhac, “Cross-layer federated learning for lightweight IoT intrusion detection systems”, Sensors, vol.23, no .16, pp.7038, 2023.
  • A. R. Abdulla, and N.G.M. Jameel, “A review on IoT intrusion detection systems using supervised machine learning: Techniques, datasets, and algorithms”, UHD Journal of Science and Technology, vol.7, no. 1, pp.53-65, 2023.
  • N. Tekin, A. Acar, A. Aris, A. S. Uluagac, and V. C. Gungor, “Energy consumption of on-device machine learning models for IoT intrusion detection”, Internet of Things, vol.21, pp.100670,2023.
  • M. Catillo, A. Pecchia, and U. Villano, “CPS-GUARD: Intrusion detection for cyber-physical systems and IoT devices using outlier-aware deep autoencoders”, Computers & Security, vol.129, pp.103210, 2023.
  • F. Nielsen, “On a generalization of the Jensen–Shannon divergence and the Jensen–Shannon centroid”, Entropy, vol.22, no.2, pp.221, 2020.
  • The CIC IoT dataset 2023 is taken from, “https://www.unb.ca/cic/datasets/iotdataset-2023.html” accessed on 2024.
    •

Access options

  • Price $
  • Offer $
Buy article PDF

DOI : https://doi.org/10.46253/jnacs.v7i3.a4

Author information

Affiliations

Department of Computer Science University of Texas at Arlington, United States shanoorafreen.2311@gmail.com

Publisher Information

  • Received

    9 July

  • Revised

    9 August

  • Accepted

    2 September

Keywords
IoT, intrusion detection, deep learning, feature fusion, Jensen Shannon similarity.

Publisher : Resbee Info Technologies Pvt Ltd