Е-Публикации
Технически университет - София

Abstract: The increasing complexity and sophistication of cyber threats pose significant challenges to network security. Detecting suspicious patterns in network traffic-such as unusual activity, unexpected communications, and atypical data patterns - is critical for identifying potential cyber-attacks and unauthorized network use. In this study, we propose a modular neural network approach, integrating Recurrent Neural Networks (RNN) and Nonlinear AutoRegressive eXogenous (NARX) models, to effectively detect these anomalies. The modular structure divides the problem into manageable subproblems, allowing for enhanced accuracy and flexibility. The RNN's ability to process sequential data, combined with the NARX model's capacity to capture both internal and external dependencies, makes this hybrid approach particularly effective in analyzing complex network traffic patterns. We trained and tested the proposed model using both typical and atypical network traffic data, achieving a mean squared error close to zero during the training phase. This research contributes to the development of more resilient and adaptive cybersecurity solutions, capable of safeguarding networks against evolving threats.

References

1. Ahmed, M., Mahmood, A. N., & Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19-31.
2. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control. Wiley.
3. Chen, J., & Li, X. (2021). Anomaly Detection in Wireless Sensor Networks with Unsupervised Learning. Sensors, 21(15), 5123.
4. Haykin, S. (1998). Neural Networks: A Comprehensive Foundation. Prentice Hall.
5. Kim, S., Cho, S., & Kwon, H. (2020). Detection of DDoS Attacks Using LSTM in the Software-Defined Network Environment. IEEE Access, 8, 167035-167045.
6. Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019.
7. Roy, S., Chakraborty, P., Pradhan, R., & Rai, S. (2021). Cyber Intrusion Detection using Recurrent Neural Networks and Deep Learning. Journal of Cyber Security Technology, 5(1), 33-48.
8. Sotirov, S., Krawczak, M.: Generalized net model of recurrent neural network. In: Proceedings of the 11th International Workshop on GNs and Second Int. Workshop on GNs, IFSs, KE, pp. 14–20 London, 9–10 July 2010
9. Sotirov, S., Sotirova, E., Atanassova, V., Atanassov, K., Castillo, O., Melin, P., ... & Surchev, S. (2018). A hybrid approach for modular neural network design using intercriteria analysis and intuitionistic fuzzy logic. Complexity, 2018(1), 3927951.
10. Sotirov, S., Sotirova, E., Melin, P., Castillo, O., & Atanassov, K., Modular Neural Network Preprocessing Procedure with Intuitionistic Fuzzy InterCriteria Analysis Method. In Flexible Query Answering Systems 2015, Springer International Publishing,2016, 175-186
11. Yin, C., Zhu, Y., Fei, J., & He, X. (2017). A deep learning approach for intrusion detection using recurrent neural networks. IEEE Access, 5, 21954-21961.
12. Zhou, J., Jin, B., & Zhang, Z. (2021). Anomaly Detection in Wireless Networks with Recurrent Neural Networks. Wireless Personal Communications, 119(1), 223-238.

Issue

Copyright IEEE