Distributed denial of service attack detection using machine learning classifiers

Online services risk distributed denial of service attacks due to their availability. These attacks overload system resources and make them unusable by legitimate users. This study aims to analyse publicly available datasets spanning three years. This analysis uses machine learning classifiers to detect and classify the attacks. The experimental results of this approach demonstrate precise attack detection and classification with minimal false-positive rates. This study utilised publicly available datasets and employed machine learning classifiers. Decision tree and random forest classifiers achieved the highest accuracy rates, and the K-nearest neighbours and support vector machine classifiers took longer to execute. Correlation coefficient and recursive feature elimination approaches gave more insights into the features of the utilised datasets. Machine learning models were used to analyse attacks and determine the best accuracies for detection. Machine learning provided favourable detection rates for DDoS attacks, underscoring the importance of algorithm selection.