A Machine Learning Driven Intrusion Detection Model Using Logistic Regression and Transfer Learning


Authors : Promise Enyindah; Umejuru Daniel

Volume/Issue : Volume 11 - 2026, Issue 1 - January

Google Scholar : https://tinyurl.com/5x56btx9

Scribd : https://tinyurl.com/4njry98h

DOI : https://doi.org/10.38124/ijisrt/26jan777

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Network intrusion detection systems (IDS) play a critical role in protecting modern network communications by analyzing patterns in network traffic to identify potential attacks and policy violations. Recent advances have seen IDSs leverage both traditional and deep machine learning techniques, though developing such models often demands large datasets, extensive computational resources, and multiple training iterations. This study presents a network intrusion detection approach based on transfer learning, aiming to improve detection efficiency while reducing the cost and complexity of model training. Two pre-trained convolutional neural network (CNN) models were adapted for IDS tasks using knowledge transfer, enabling the integration of predictions into a single enhanced model. The system was trained and evaluated using the NLS-KDD benchmark dataset, covering normal traffic as well as probing, Denial-of-Service (DoS), user-to-root (U2R), and remote-to-local (R2L) attack types. Experimental results show that the transfer learning approach achieved a prediction accuracy of 96.52%, significantly outperforming a traditional logistic regression model, which achieved 66.56%. These findings demonstrate that transfer learning can effectively enhance IDS performance, improving both reliability and accuracy in detecting diverse network threats.

Keywords : Logistic Regression, Intrusion, Detection, Attack, Transfer Learning.

References :

  1. Albulayhi, K., Abu Al-Haija, D., Alsuhibany, S. A.,. Jillepalli, A. A.,. Ashrafuzzaman,M.  and Sheldon, F. T.(2025) IoT intrusion detection using machine learning with a novel high performing feature selection method, Applied Sciences, 12(10), 1-20, doi: 10.3390/app12105015.
  2. Ambusaidi M. et al (2022), “Building an intrusion detection system using a filter-based feature selection algorithm”, International Journal of Innovative Research & Studies: 112(23):25-27.
  3. Butun Ismail(2023)., “Prevention and Detection of Intrusions in Wireless Sensor Networks”, Scholar Commons: 15
  4. Chawla S. (2023), Deep Learning based Intrusion Detection System for Internet of Things: 2
  5. Diogenes, Y. and Ozkaya,E. (2023) Counter modern threats and employ state-of-the-art tools and techniques to protect your organization against cybercriminals, in Cybersecurity – Attack and Defense Strategies, 2nd Editio., Packt Publishing Ltd., 2-30
  6. Furnell, S., Jusoh, A. and Katsabas, D. (2024), The Challenges of Understanding and Using Security: A Survey of End-users, Computer and Security, 25, 27–35.
  7. Ghosal A. and Halder S. (2022), Intrusion Detection in Wireless Sensor Networks: Issues, Challenges and Approaches,  Research Gate: 1(12), 2-23.
  8. Hu Y. et al (2020), ” A survey of intrusion detection on industrial control systems”, International Journal of Distributed Sensor Network: 2-3
  9. Mohammad  M. et al (2021),  A Novel Local Network Intrusion Detection System Based on Support Vector Machine”, Journal of Computer Science, 7(10), 1560-1568.
  10. Parag K. et al (2021), “Intrusion Detection System for Cloud Computing”, International Journal of Scientific & Technology Research,1(4), 12-16.
  11. Sheikh A. et al (2022), Analytical Study on Hybrid Approach towards Intrusion Detection System for Wireless Sensor Network: 3
  12. Singh, A., Amutha, J. Nagar, J., Sharma, S. and C.-C. Lee, (2022) LT-FS-ID: Log-transformed feature learning and feature-scaling-based machine learning algorithms to predict the k-barriers for intrusion detection using wireless sensor network, Sensors, 22(3),  1070, doi: 10.3390/s22031070.
  13. Solanki, S., Gupta, C. and Rai, K.(2020), A Survey on Machine Learning based Intrusion Detection System on NSLKDD Dataset, International Journal of Computer Applications, 176(20), 121- 128.
  14. Stosic L. (2022), “Computer Security and security technmologies”, Research Gate: 25.
  15. Surantha N. and Wicaksono W. (2019), An IoT based House Intruder Detection and Alert System using Histogram of Oriented Gradients”, Journal of Computer Science, 31(41), 1101-1121
  16. Subramaniam  M and Kathirvel  K (                2020), Improved Intrusion Detection and Response  System for Wireless Sensor Network, International Journal of Forensic Science 10(2), 23-30.
  17. Talukder, A., Hasan, K. F., Islam, M., Uddin, A., Akhter, A., Yousuf, M., Alharbi, F., and Moni, M a.(2023), A Dependable Hybrid Machine Learning Model for Network Intrusion Detection, Journal of Information Security and Applications,  arXiv:2212.04546v2 [cs.CR] 27 Jan 2023,  1-44.
  18. Tan, Z. Jamdagni, X. He, X. Nanda, P. and Liu, R. P. (2024), A system for denial-of-service attack detection based on multivariate correlation analysis, IEEE Transactions on Parallel and Distributed Systems, 25, 447–456.
  19. Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., and Liu, C. (2021). A survey on deep transfer learning. In Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III 27 (pp. 270-279).
  20. Tsiakmaki, M., Kostopoulos, G., Kotsiantis, S., & Ragos, O. (2020). Transfer learning from deep neural networks for predicting student performance. Applied Sciences, 10(6), 2145.
  21. Vadhil, F. A., Salihi, M. L. and Nanne, M. F.(2024), Machine learning-based intrusion detection system for detecting web attacks, IAES International Journal of Artificial Intelligence (IJ-AI), 13(1), 711~721
  22. Usha D. And Suganthi S. (2023), A Survey of Intrusion Detection System in IoT Devices, International Journal of Advanced Research (IJAR): 23, 12-23.
  23. Wang K. and Stolfo S., (2019), “Anomalous Payload-based Network Intrusion Detection”:12-23
  24. Wazid M. (2021), Design and Analysis of Intrusion Detection Protocols for Hierarchical Wireless Sensor Networks, Design and Analysis of Intrusion Detection Protocols for Hierarchical Wireless Sensor Networks, 1(23), 23-28.
  25. Yao J. (2020), An Enhanced Support Vector Machine Model for Intrusion Detection, 4(5),1-4.

Network intrusion detection systems (IDS) play a critical role in protecting modern network communications by analyzing patterns in network traffic to identify potential attacks and policy violations. Recent advances have seen IDSs leverage both traditional and deep machine learning techniques, though developing such models often demands large datasets, extensive computational resources, and multiple training iterations. This study presents a network intrusion detection approach based on transfer learning, aiming to improve detection efficiency while reducing the cost and complexity of model training. Two pre-trained convolutional neural network (CNN) models were adapted for IDS tasks using knowledge transfer, enabling the integration of predictions into a single enhanced model. The system was trained and evaluated using the NLS-KDD benchmark dataset, covering normal traffic as well as probing, Denial-of-Service (DoS), user-to-root (U2R), and remote-to-local (R2L) attack types. Experimental results show that the transfer learning approach achieved a prediction accuracy of 96.52%, significantly outperforming a traditional logistic regression model, which achieved 66.56%. These findings demonstrate that transfer learning can effectively enhance IDS performance, improving both reliability and accuracy in detecting diverse network threats.

Keywords : Logistic Regression, Intrusion, Detection, Attack, Transfer Learning.

Paper Submission Last Date
31 - January - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe