Ensemble Deep Learning-Based Ddos Classification in Sflow-Enabled Software-Defined Networking

Ensemble Deep Learning-Based Ddos Classification in Sflow-Enabled Software-Defined Networking
  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-6
Year of Publication : 2025
Author : S. Natesan, C. Sivakumar
DOI : 10.14445/22315381/IJETT-V73I6P124

How to Cite?
S. Natesan, C. Sivakumar, "Enhancing Credit Card Registration Form Processing with Fine-Tuned Transformer-Based OCR Models," International Journal of Engineering Trends and Technology, vol. 73, no. 6, pp.292-301, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I6P124

Abstract
Software-Defined Networking (SDN) exhibits a programmable architecture that decouples the control plane from the data plane, improving network management. On the other hand, this centralizing makes the network more susceptible to Distributed Denial of Service (DDoS) attacks, which might easily overwhelm the resources of SDN and lead to network failure. Early identification of such risks is necessary for the continuous stability of SDN. The slow approach's real-time traffic monitoring capabilities enable one to efficiently sample flow-based data. This helps reduce processing overhead in network switches and provides good attack detection. Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), and ResNet make up the Stacked Deep Ensemble Model applied in this research project; all these components contribute to accurate DDoS classification achievement. GNS 3 models the topology of the network while the SDN environment is built using the ONOS SDN Controller. SFlow helps with data collecting; Prometheus acts as a time-series database to store traffic data. Using both the NSL-KDD and UNSW-NB15 benchmark datasets, the proposed approach is assessed to be resilient over a wide range of attack scenarios. Since the ensemble model reduces the number of false positives found and efficiently achieves higher classification accuracy, the experiments show that it performs better than conventional detection methods.

Keywords
DDoS detection, Software-Defined Networking, sFlow, Deep learning, Ensemble model.

References
[1] Muruganantham Ponnusamy et al., “Design and Analysis of Text Document Clustering using Salp Swarm Algorithm,” The Journal of Supercomputing, vol. 78, no. 14, pp. 16197-16213, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Imran et al., “A Topical Review on Machine Learning, Software Defined Networking, Internet of Things Applications: Research Limitations and Challenges,” Electronics, vol. 10, no. 8, pp. 1-28, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Manivel Kandasamy et al., “QOS Design using Mmwave Backhaul Solution for Utilising Underutilised 5G Bandwidth in GHZ Transmission,” 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS), Coimbatore, India, pp. 1615-1620, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] N. Yuvaraj et al., An Artificial Intelligence Based Sustainable Approaches-IoT Systems for Smart Cities, AI Models for Blockchain-Based Intelligent Networks in IoT Systems, Springer, pp. 105-120, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Muhammad Afaq, Shafqat Ur Rehman, and Wang-Cheol Song, “A Framework for Classification and Visualization of Elephant Flows in SDN-Based Networks,” Procedia Computer Science, vol. 65, pp. 672-681, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Meng Wang, Yiqin Lu, and Jiancheng Qin Source-Based, “Source-Based Defense against DDoS Attacks in SDN Based on sFLOW and SOM,” IEEE Access, vol. 10, pp. 2097-2116, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Nadhir Fachrul Rozam, and Mardhani Riasetiawan, “XGBoost Classifier for DDOS Attack Detection in Software Defined Network using sFlow Protocol,” International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 2, pp. 718-725, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Adeniji Oluwashola David, and Oluwabusayo Israel Omotosho, “Scalable Flow Based Management Scheme in Software Define Network (SDN) Using sFlow,” WSEAS Transactions on Computers, vol. 22, pp. 64-69, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Neelam Gupta et al., “DDoS Attack Defence Mechanism Using sFlow,” 2022 International Conference on Data Analytics for Business and Industry (ICDABI), Sakhir, Bahrain, pp. 302-308, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Afsaneh Banitalebi Dehkordi, MohammadReza SoltanaghaeI, and Farsad Zamani Boroujeni, “The DDoS Attacks Detection through Machine Learning and Statistical Methods in SDN,” The Journal of Supercomputing, vol. 77, no. 3, pp. 2383-2415, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Mahmoud Said El Sayed et al., “A Flow-Based Anomaly Detection Approach with Feature Selection Method against Ddos Attacks in SDNs,” IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 4, pp. 1862-1880, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Rochak Swami, Mayank Dav, and Virender Ranga, “Detection and Analysis of TCP-SYN DDoS Attack in Software-Defined Networking,” Wireless Personal Communications, vol. 118, no. 4, pp. 2295-2317, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mohammad Javad Shayegan, and Amirreza Damghanian, “A Method for DDoS Attacks Prevention Using SDN and NFV,” IEEE Access, vol. 12, pp. 108176-108184, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Rochak Swami, Mayank Dave, and Virender Ranga, “QR-based Approach for DDoS Detection and Mitigation in SDN,” Defence Technology, vol. 25, pp. 76-87, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Kun Jia et al., “A lightweight DDoS Detection Scheme under SDN Context,” Cybersecurity, vol. 5, no. 1, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Naziya Aslam, Shashank Srivastava, and M.M. Gore, “ONOS Flood Defender: An Intelligent Approach to Mitigate DDoS Attack in SDN,” Transactions on Emerging Telecommunications Technologies, vol. 33, no. 9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]