Efficient DDoS Detection in Software-Defined Networking: A Machine Learning Perspective

DDoS attacks are among of the most dangerous forms of attack these days. They are the reason for many security issues in this era all around the globe, particularly in the landscape of SDN where core SDN controlllers are prone to attacks due to their centralized nature. The primary objective of this work is to further the use of machine learning in SDN systems for DDoS attack detection. We performed this research on five machine learning systems, namely Artificial Neural Networks (ANN), Support Vector Classifier (SVC), Decision Tree (DT), and Gradient Boosting Classifier (GBC) a hybrid SVC+GBC model with the aid of the DataSet Sdn. The dataset encompasses standard and attacked data of traffic, around 80 factors are included such as packet and protocol details. One hot encoding and feature selection were some of the data pre-processing methods that were introduced to enhance the models. The evaluation methods were accuracy, F1 score, recall, and precision. Our SVC+GBC hybrid model surpassed all the standalone algorithms, 99.77% accuracy and an F1 Score of 99.76%. To sum up, the use of detection methods based on machine learning can greatly boost the defense of SDN network to DDoS attacks.