AI-Augmented Traffic Analysis for Intrusion Detection in Software-Defined Networks: A Hybrid Approach
Published 23-06-2023
Keywords
- AI,
- machine learning,
- deep learning,
- intrusion detection system,
- Software-Defined Networks
- anomaly detection,
- traffic analysis ...More
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
Abstract
In the era of rapidly advancing network technologies, Software-Defined Networking (SDN) has emerged as a promising architecture for managing and controlling network traffic. However, the openness and centralized control of SDN introduce unique security challenges, particularly in detecting and mitigating intrusions. Traditional intrusion detection systems (IDS) often struggle to keep pace with the dynamic and complex nature of SDN environments. This paper proposes an AI-augmented traffic analysis framework for intrusion detection in SDNs, leveraging a hybrid approach that combines machine learning (ML) and deep learning (DL) techniques. The hybrid system aims to enhance detection accuracy, reduce false positives, and improve real-time performance. We explore the integration of AI models into SDN traffic flows, examining their application in anomaly detection, pattern recognition, and predictive modeling. Through a detailed review of existing research, we assess the potential and limitations of AI-driven IDS in SDNs, providing a roadmap for future research in this area.
Downloads
References
- Ahmed, M., & Younis, M. (2020). AI-powered traffic analysis for network security in SDNs. International Journal of Computer Networks and Communications, 12(3), 45-58.
- Bao, Z., & Chen, L. (2021). Hybrid deep learning for intrusion detection in SDN-based networks. IEEE Access, 9, 84532-84545.
- Ali, Syed Afraz. "Designing Secure and Robust E-Commerce Plaform for Public Cloud." The Asian Bulletin of Big Data Management 3.1 (2023): 164-189.
- Bhattacharya, M., & Das, A. (2020). Machine learning algorithms for intrusion detection in SDNs. Journal of Network and Computer Applications, 132, 12-24.
- Chen, J., & Lee, S. (2022). Enhancing intrusion detection in SDN using AI-based anomaly detection systems. Journal of Computing and Security, 30(4), 221-238.
- Ding, C., & Zhao, Z. (2020). Real-time traffic analysis and intrusion detection in SDNs. IEEE Transactions on Network and Service Management, 17(5), 1056-1070.
- Guo, X., & Wu, T. (2021). A hybrid model for SDN traffic analysis and intrusion detection. ACM Computing Surveys, 54(3), 45-58.
- Jiang, F., & Wang, Y. (2020). Reinforcement learning for anomaly detection in SDNs. Proceedings of the 2020 IEEE International Conference on Machine Learning and Computing, 33-42.
- Khan, I., & Shah, M. (2021). Traffic analysis for intrusion detection in SDN: A deep learning approach. IEEE Journal on Selected Areas in Communications, 39(6), 1771-1783.
- Li, T., & Zhang, X. (2020). Hybrid intrusion detection system for SDN-based network security. Journal of Security and Communication Networks, 22(7), 1574-1589.