Real-Time Anomaly Detection in Network Traffic Using Hybrid AI Models
Keywords:
Network Security, Anomaly Detection, Artificial Intelligence, Machine Learning, Deep Learning, Cybersecurity, Intrusion Detection.Abstract
The increasing complexity of modern network environments has led to a significant rise in cyber threats, making effective network security a critical requirement. Traditional intrusion detection systems often struggle to identify unknown attacks and generate high false positive rates. Real-time anomaly detection has emerged as an essential approach for identifying suspicious activities and preventing security breaches before they cause significant damage.
This study proposes a hybrid Artificial Intelligence (AI) framework for real-time anomaly detection in network traffic. The proposed model combines Machine Learning and Deep Learning techniques to improve detection accuracy and adaptability. Random Forest is used for feature selection and classification, while Long Short-Term Memory (LSTM) networks capture temporal patterns and behavioral characteristics within network traffic data. The integration of these models enables efficient identification of both known and previously unseen cyber threats.
The methodology involves data collection, preprocessing, feature extraction, model training, and performance evaluation using standard cybersecurity datasets. Experimental results demonstrate that the hybrid AI model achieves higher accuracy, improved detection rates, and lower false positive rates compared to conventional approaches. The framework effectively detects various network attacks while maintaining real-time operational performance.
The findings indicate that hybrid AI models provide a scalable and intelligent solution for modern cybersecurity systems, enhancing network monitoring capabilities and supporting proactive threat detection in dynamic network environments.
References
1. Ahmed, M., Mahmood, A. N., & Hu, J. (2018). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19–31.
2. Aljawarneh, S., Aldwairi, M., & Yassein, M. B. (2018). Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. Journal of Computational Science, 25, 152–160.
3. Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2020). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, 102419.
4. Vinayakumar, R., Alazab, M., Soman, K. P., Poornachandran, P., & Al-Nemrat, A. (2019). Deep learning approach for intelligent intrusion detection system. IEEE Access, 7, 41525–41550.
5. Gajula, S. (2024). Adaptive zero trust architecture for securing financial microservices. Computer Fraud & Security, 643-655.
6. Shone, N., Ngoc, T. N., Phai, V. D., & Shi, Q. (2018). A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(1), 41–50.
7. Kasongo, S. M., & Sun, Y. (2020). Performance analysis of intrusion detection systems using machine learning algorithms. Electronics, 9(10), 1684.
8. Verkerken, M., Baesens, B., & Verbeke, W. (2022). Towards automated network intrusion detection using deep learning. Computers & Security, 116, 102629.
9. Maseer, Z. K., Yusof, R., Bahaman, N., Mostafa, S. A., & Foozy, C. F. M. (2021). Benchmarking of machine learning techniques for network intrusion detection. IEEE Access, 9, 22351–22370.
10. Gajula, S. (2025). Cybersecurity Risk Prediction Using Graph Neural Networks. Authorea Preprints.
11. Alsaedi, A., Moustafa, N., Tari, Z., Mahmood, A., & Anwar, A. (2020). Network anomaly detection using machine learning techniques. Future Generation Computer Systems, 108, 1–14.
12. Roy, S. S., Mallik, A., Gulati, R., Obaidat, M. S., & Krishna, P. V. (2021). Deep learning enabled anomaly detection in cybersecurity. Computers & Electrical Engineering, 96, 107456.
13. Ullah, I., Mahmoud, Q. H., & Alghamdi, A. (2022). Intrusion detection using hybrid machine learning and deep learning models. Sensors, 22(18), 6871.
14. Javaid, A., Niyaz, Q., Sun, W., & Alam, M. (2019). A deep learning approach for network intrusion detection systems. EAI Endorsed Transactions on Security and Safety, 6(19), 1–10.
15. Khraisat, A., Gondal, I., Vamplew, P., & Kamruzzaman, J. (2019). Survey of intrusion detection systems: Techniques, datasets, and challenges. Cybersecurity, 2(1), 20.
16. Moustafa, N., & Slay, J. (2019). UNSW-NB15: A comprehensive data set for network intrusion detection systems. Military Communications and Information Systems Conference Proceedings, 1–6.
17. Ferrag, M. A., Maglaras, L., Ahmim, A., Derdour, M., & Janicke, H. (2022). RDTIDS: Rules and deep transfer learning-based intrusion detection system. Future Internet, 14(3), 82.
18. Zhang, H., Wang, X., Liu, Y., & Chen, J. (2023). Hybrid deep learning framework for real-time network anomaly detection. IEEE Access, 11, 45872–45885.
19. Alzahrani, B., Alghamdi, A., & Alshahrani, S. (2024). Artificial intelligence-driven cybersecurity: A hybrid approach for intrusion detection and threat analysis. Sensors, 24(5), 1742.
20. Kumar, P., Gupta, R., Sharma, S., & Singh, A. (2024). Real-time anomaly detection in network traffic using hybrid machine learning and deep learning models. Journal of Cyber Security Technology, 8(2), 85–102.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Bishop International Journal of Mathematics and Computer Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
