DDoS Attack Detection Using Ensemble Machine Learning

A distributed denial of service (DDoS) attack targets at hindering authorized individuals from accessing a server or website by flooding it with traffic from many sources. To avoid a DDoS attack from damaging the target system, detection is required. The system becomes unsafe as a result of this attack. The paper provides an ensemble machine learning technique-based DDoS attack detection model. To choose the most significant characteristics from the Kaggle dataset, three feature selection techniques-ANOVA, mutual information, and feature importance are applied. The traditional machine learning methods K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Naive Bayes (NB) are then used with the chosen features. Then, four ensemble methods were created by combining three models from these four traditional machine learning algorithm using hard ensemble voting. By evaluating precision, recall, F1-score, and accuracy, the experiment’s outcome is determined. After all the experiments, the result shows that the features selected by feature importance technique give the highest accuracy, 98.86% with the ensemble voting classifier by the combinations of KNN, SVM, and DT.