TCP/UDP-Based Exploitation DDoS Attacks Detection Using AI Classification Algorithms with Common Uncorrelated Feature Subset Selected by Pearson, Spearman and Kendall Correlation Methods

The Distributed Denial of Service (DDoS) attack is a serious cyber security that attempts to disrupt the availability principle computer networks and information systems. It's critical detect DDoS attacks quickly accurately while using as less computing power possible in order minimize damage cost efficient. This research proposes fast high-accuracy detection approach by features selected proposed method for Exploitation-based attacks. Experiments are carried out on CICDDoS2019 datasets Syn flood, UDP UDP-Lag, well customized dataset. In addition, experiments were also conducted dataset was constructed combining three datasets. Pearson, Spearman, Kendall correlation techniques have been used find un-correlated feature subsets. Then, among subsets, choose common features. On datasets, classification applied these conventional classifiers Logistic regression, Decision tree, KNN, Naive Bayes, bagging classifier Random forest, boosting Ada boost, Gradient neural network-based Multilayer perceptron. performance algorithms evaluated terms accuracy, precision, recall, F1-score, specificity, log loss, execution time, K-fold cross-validation. Finally, tested with all dataset’s sets.