Deep Learning-Based Network Traffic Signal Analysis for Intelligent Cyber Threat Detection

Rahul Vijay Kotawadekar; Dr. Suhasini Vijaykumar; Dr. M. Prabha; Rohit Shantinath Barwade; Dr. Banani Das; Dr. Geeta Kakarla

doi:10.29284/rp5sny71

Authors

Rahul Vijay Kotawadekar Research Scholar, Department of Computer Applications, Bharati Vidyapeeth's Institute of Management & Information Technology, Affiliated to University of Mumbai, Navi Mumbai, India, Orcid ID: 0009-0002-1923-6139
Dr. Suhasini Vijaykumar Professor and Principal, Department of Computer Applications, Bharati Vidyapeeth's Institute of Management & Information Technology, Affiliated to University of Mumbai, Navi Mumbai, India, Orcid ID: 0000-0001-9885-1046
Dr. M. Prabha Assistant Professor, Department of Electronics and Communication Engineering, Vel Tech Rangarajan,
Rohit Shantinath Barwade Assistant Professor, D. Y. Patil Prathisthan's College of Engineering, Salokhenagar (DYPSN), Kolhapur, Maharashtra, Orcid ID: 0000-0002-3460-2013
Dr. Banani Das Assistant Professor, Faculty of Computer Technology, Assam down town University, Guwahati, Assam, India
Dr. Geeta Kakarla Associate Professor, Sreenidhi Institute of Science and Technology, Orcid ID: 0000-0002-6643-275X

DOI:

https://doi.org/10.29284/rp5sny71

Keywords:

traffic signal analysis, cyber threat detection, deep learning, intrusion detection, signal analysis.

Abstract

Cybersecurity Networked systems are using more and more traffic-level monitoring as a basis, whereas most ways of detecting intrusions view network traffic as a static set of records instead of examining its natural signal-like behavior. In this work, the authors attempt to investigate the question of whether modeling network traffic as a signal and using deep learning can be effectively used to distinguish between normal and malicious activity while being interpretable. The UNSW-NB15 dataset was used with its original training and testing partitions, and traffic was analyzed from both temporal and statistical perspectives. Feature relevance was assessed using mutual information to identify discriminative traffic attributes, and a feedforward neural network was trained using standardized flow-level features for binary threat detection. The evaluation achieved an overall accuracy of 0.777, with an attack-class F1-score of 0.825 and an area under the ROC curve of approximately 0.89, indicating stable discrimination under class imbalance. The results show that traffic intensity, aggregation, and duration features provide strong discriminatory capability without reliance on payload inspection. These findings suggest that a signal-oriented view of network traffic, combined with deep learning, offers a practical and interpretable approach for cyber threat detection, while highlighting the need for future work on sequence-aware modeling and validation across diverse network environments.

References

1. Qadri, S.S.S.M., Gökçe, M.A. and Öner, E., 2020. State-of-art review of traffic signal control methods: challenges and opportunities. European transport research review, 12(1), p.55.

2. Savithramma, R.M., Sumathi, R. and Sudhira, H.S., 2022. A comparative analysis of machine learning algorithms in design process of adaptive traffic signal control system. In Journal of Physics: Conference Series (Vol. 2161, No. 1, p. 012054). IOP Publishing.

3. Eom, M. and Kim, B.I., 2020. The traffic signal control problem for intersections: a review. European transport research review, 12(1), p.50.

4. Perrine, K.A., Levin, M.W., Yahia, C.N., Duell, M. and Boyles, S.D., 2019. Implications of traffic signal cybersecurity on potential deliberate traffic disruptions. Transportation research part A: policy and practice, 120, pp.58-70.

5. Feng, Y., Huang, S.E., Wong, W., Chen, Q.A., Mao, Z.M. and Liu, H.X., 2022. On the cybersecurity of traffic signal control system with connected vehicles. IEEE Transactions on Intelligent Transportation Systems, 23(9), pp.16267-16279.

6. Papanikolaou, A., Alevizopoulos, A., Ilioudis, C., Demertzis, K. and Rantos, K., 2023. An autoML network traffic analyzer for cyber threat detection. International Journal of Information Security, 22(5), pp.1511-1530.

7. Coulter, R., Han, Q.L., Pan, L., Zhang, J. and Xiang, Y., 2019. Data-driven cyber security in perspective—Intelligent traffic analysis. IEEE transactions on cybernetics, 50(7), pp.3081-3093.

8. Ma, C., 2021. Smart city and cyber-security; technologies used, leading challenges and future recommendations. Energy Reports, 7, pp.7999-8012.

9. Sun, X., Yu, F.R. and Zhang, P., 2021. A survey on cyber-security of connected and autonomous vehicles (CAVs). IEEE Transactions on Intelligent Transportation Systems, 23(7), pp.6240-6259.

10. Kalinin, M., Krundyshev, V. and Zegzhda, P., 2021. Cybersecurity risk assessment in smart city infrastructures. Machines, 9(4), p.78.

11. Alazab, M. and Tang, M. eds., 2019. Deep learning applications for cyber security. Springer.

12. Zhang, Z., Ning, H., Shi, F., Farha, F., Xu, Y., Xu, J., Zhang, F. and Choo, K.K.R., 2022. Artificial intelligence in cyber security: research advances, challenges, and opportunities. Artificial Intelligence Review, 55(2), pp.1029-1053.

13. Liu, L., Wang, P., Lin, J. and Liu, L., 2020. Intrusion detection of imbalanced network traffic based on machine learning and deep learning. IEEE access, 9, pp.7550-7563.

14. Khalaf, L.I., Alhamadani, B., Ismael, O.A., Radhi, A.A., Ahmed, S.R. and Algburi, S., 2024, May. Deep learning-based anomaly detection in network traffic for cyber threat identification. In Proceedings of the Cognitive Models and Artificial Intelligence Conference (pp. 303-309).

15. Xuan, C.D., Duong, D. and Dau, H.X., 2021. A multi-layer approach for advanced persistent threat detection using machine learning based on network traffic. Journal of Intelligent & Fuzzy Systems, 40(6), pp.11311-11329.

16. Islam Rifa, N.A., 2025. UNSW-NB15 dataset. Kaggle [Dataset]. Available at: https://www.kaggle.com/datasets/nafisaislamrifa/unsw-nb15

17. Vinayakumar, R., Alazab, M., Soman, K.P., Poornachandran, P., Al-Nemrat, A. and Venkatraman, S., 2019. Deep learning approach for intelligent intrusion detection system. IEEE access, 7, pp.41525-41550.

18. Ali, S., Abusabha, O., Ali, F., Imran, M. and Abuhmed, T., 2022. Effective multitask deep learning for iot malware detection and identification using behavioral traffic analysis. IEEE Transactions on Network and Service Management, 20(2), pp.1199-1209.

19. Umer, M., Sadiq, S., Karamti, H., Alhebshi, R.M., Alnowaiser, K., Eshmawi, A.A., Song, H. and Ashraf, I., 2022. Deep learning-based intrusion detection methods in cyber-physical systems: Challenges and future trends. Electronics, 11(20), p.3326.

20. Awajan, A. (2023). A novel deep learning-based intrusion detection system for IOT networks. Computers, 12(2), 34.

21. Ahmed, N., Ngadi, A.B., Sharif, J.M., Hussain, S., Uddin, M., Rathore, M.S., Iqbal, J., Abdelhaq, M., Alsaqour, R., Ullah, S.S. and Zuhra, F.T., 2022. Network threat detection using machine/deep learning in sdn-based platforms: a comprehensive analysis of state-of-the-art solutions, discussion, challenges, and future research direction. Sensors, 22(20), p.7896.

22. Sewak, M., Sahay, S.K. and Rathore, H., 2023. Deep reinforcement learning in the advanced cybersecurity threat detection and protection. Information Systems Frontiers, 25(2), pp.589-611.

23. Abu Al-Haija, Q. and Zein-Sabatto, S., 2020. An efficient deep-learning-based detection and classification system for cyber-attacks in IoT communication networks. Electronics, 9(12), p.2152.

24. Ferrag, M.A., Shu, L., Friha, O. and Yang, X., 2021. Cyber security intrusion detection for agriculture 4.0: Machine learning-based solutions, datasets, and future directions. IEEE/CAA Journal of Automatica Sinica, 9(3), pp.407-436.