• Jean Paul Ndayizigiye

Software-defined networking (SDN) disrupts the vertical integration of current Internet architecture and makes the network programmable from a logically centralized control point. Although centralized network control provides a lots advantages, it remains a challenge for researchers due to attacks against the SDN framework. Identifying DDoS attacks using machine learning is fundamentally a classification issue. In this article, we propose a model based on machine learning to detect a denial of service (DoS) attack in data plane devices, i.e., the OpenFlow switches, resulting from flow-table overflow. An SDN dataset was generated using Mininet and Ryu controllers. The split of the dataset was set at 70% training and 30% testing sets. The five features from a batch of 21 features are extracted using the ExtraTreesClassifier. Further, in this article, two algorithms, (i) Decision Tree (DT) and (ii) K-Nearest Neighbor (KNN), have been tested to detect DDoS attacks and classify the packet as either normal or an attack. The results showed an accuracy of 99.77of Decision Trees, and K-Nearest Neighbor achieved accuracy of 99.38%. We found that Decision Trees generates the best result.

software defined networking, distributed denial of service attacks, machine learning algorithms, decision trees and k-nearest neighbor

"Utilizing Machine Learning Algorithms for Early Detection of DDoS Attacks in Software-Defined Networking.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.o372-o384, May-2023, Available :http://www.jetir.org/papers/JETIR2305F48.pdf

"Utilizing Machine Learning Algorithms for Early Detection of DDoS Attacks in Software-Defined Networking.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppo372-o384, May-2023, Available at : http://www.jetir.org/papers/JETIR2305F48.pdf