A Hybrid Machine Learning Approach for Web-Based Anomaly Detection in Network Traffic: Strengthening Cybersecurity Education and Advancing SDGs 4 and 9

Emmanuel John Anagu, Precious Njoya Philip

Abstract


The increasing sophistication of cyber threats and the complexity of network traffic demand innovative strategies in both cybersecurity systems and digital education. This study proposes a hybrid machine learning approach (combining Support Vector Machine (SVM), Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM)) to detect anomalies in network traffic with high accuracy. Trained on the CIC-DDoS2019 dataset, the models achieved over 99% accuracy, with the hybrid stacking model performing most effectively. The model was deployed in a real-time web-based interface to serve both detection and instructional purposes. This dual-function system supports cybersecurity education by providing students with a hands-on environment to explore, analyze, and visualize network anomalies. The research contributes to SDG 4 by enhancing digital literacy and to SDG 9 by promoting technological innovation in cybersecurity. The study highlights how educational integration of AI-driven anomaly detection tools can foster a deeper understanding of network protection in the digital age.

Keywords


Anomaly detection; Cybersecurity education; Hybrid machine learning; SGDs 4; Web application

Full Text:

PDF

References


Abdallah, A. M., Alkaabi, A. S. R. O., Alameri, G. B. N. D., Rafique, S. H., Musa, N. S., and Murugan, T. (2024). Cloud network anomaly detection using machine and deep learning techniques—Recent research advancements. IEEE Access, 12, 56749–56773.

Abdelkhalek, A., and Mashaly, M. (2023). Addressing the class imbalance problem in network intrusion detection systems using data resampling and deep learning. The Journal of Supercomputing, 79(10), 10611–10644.

Ahmed, M., and Mahmood, A. N. (2015). Novel approach for network traffic pattern analysis using clustering-based collective anomaly detection. Annals of Data Science, 2(1), 111–130.

Aribisala, B., Odusanya, O., Olabanjo, O., Wahab, E., Atilola, O., and Saheed, A. (2022). Development of an Artificial Neural Network Model for Detection of COVID-19. International Journal of Scientific Advances, 3(4), 377–385.

Djenna, A., Harous, S., and Saidouni, D. E. (2021). Internet of things meet internet of threats: New concern cyber security issues of critical cyber infrastructure. Applied Sciences, 11(10), 4580.

George, A. S., Baskar, T., and Srikaanth, P. B. (2024). Cyber threats to critical infrastructure: assessing vulnerabilities across key sectors. Partners Universal International Innovation Journal, 2(1), 51-75.

Kilincer, I. F., Ertam, F., and Sengur, A. (2021). Machine learning methods for cyber security intrusion detection: Datasets and comparative study. Computer Networks, 188, 107840.

Kumar, D. A., and Venugopalan, S. (2017). Intrusion detection systems: A review. International Journal of Advanced Research in Computer Science, 8(8), 356–370.

Martins, I., Resende, J. S., Sousa, P. R., Silva, S., Antunes, L., and Gama, J. (2022). Host-based IDS: A review and open issues of an anomaly detection system in IoT. Future Generation Computer Systems, 133, 95–113.

Shahin, M., Maghanaki, M., Hosseinzadeh, A., and Chen, F. F. (2024). Advancing network security in industrial IoT: A deep dive into AI-enabled intrusion detection systems. Advanced Engineering Informatics, 62, 102685.




DOI: https://doi.org/10.17509/ijomr.v5i2.86147

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Kantor Jurnal dan Publikasi, Universitas Pendidikan Indonesia (UPI)

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

View My Stats

Indonesian Journal of Multidiciplinary Research (IJOMR) is published by Universitas Pendidikan Indonesia (UPI)