ADAPTIVE HYBRID ALGORITHM FOR CYBERATTACK PREDICTION IN SDN-BASED MEDIUM-SCALE ICT NETWORKS
Keywords:
Software-Defined Networking (SDN); cyberattack prediction; anomaly detection; Random Forest; LSTM; Reinforcement Learning; Federated Learning; medium-scale information and communication systems.Abstract
The widespread adoption of Software-Defined Networking (SDN) in medium-scale information and communication systems increases network management flexibility but introduces security risks due to the centralized controller. Various approaches based on Machine Learning, Deep Learning, statistical analysis, Reinforcement Learning, and Federated Learning have been proposed to predict cyberattacks in SDN networks. However, most existing solutions do not fully meet real-time, resource-efficient, and adaptive requirements. This paper provides an analytical review of related work and proposes a hybrid adaptive KBGM framework integrating statistical analysis, Random Forest, LSTM, RL, and FL methods to achieve high accuracy and efficient real-time performance.
References
Alqahtani, A., Alshammari, M., & Alshamrani, A. (2023). Machine learning-based hujumlarni aniqlash in SDN: A comprehensive review. IEEE Access, 11, 23456–23478. https://doi.org/10.1109/ACCESS.2023.3256789
[2] Kumar, S., & Singh, P. (2022). Random forest-based anomaly detection for SDN-enabled networks. Journal of Network and Computer Applications, 201, 103389. https://doi.org/10.1016/j.jnca.2022.103389
Zhang, Y., Li, H., & Wang, X. (2023). LSTM-based DDoS attack prediction in SDN using flow statistics. Computers & Security, 124, 102987. https://doi.org/10.1016/j.cose.2022.102987
Chen, L., & Liu, Z. (2024). Deep packet inspection in SDN using CNN for malicious payload detection. IEEE Transactions on Network and Service Management, 21(1), 456–468. https://doi.org/10.1109/TNSM.2023.3345678
Wang, J., Zhao, M., & Xu, R. (2024). A hybrid CNN–LSTM model for real-time DDoS attack prediction in SDN. Future Generation Computer Systems, 151, 123–135. https://doi.org/10.1016/j.future.2023.08.012
Rahman, M. S., Hossain, M. S., & Rahman, M. M. (2023). Entropy-based anomaly detection in SDN: A case study on ARP spoofing. Security and Communication Networks, 2023, Article ID 6689012. https://doi.org/10.1155/2023/6689012
Li, X., Yang, K., & Zhang, T. (2025). Reinforcement learning for proactive threat mitigation in SDN. ACM Transactions on Privacy and Security, 28(2), 1–25. https://doi.org/10.1145/3623456
Nguyen, T., Tran, H., & Pham, Q. (2024). Federated learning for hujumlarni aniqlash in distributed SDN environments. IEEE Internet of Things Journal, 11(5), 7890–7902. https://doi.org/10.1109/JIOT.2023.3341234
Gupta, D., Sharma, A., & Agarwal, S. (2023). Real-time hujumlarni aniqlash system for SDN using Ryu kontroller and machine learning. International Journal of Network Management, 33(2), e2345. https://doi.org/10.1002/nem.2345
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Sodiq Jumayev
This work is licensed under a Creative Commons Attribution 4.0 International License.
