An Innovative Ensemble Approach to Detecting Distributed Denial of Service Attacks Using Machine Learning

In the present era marked by rapid Internet development, there is a growing emphasis on information security. Distributed Denial of Service (DDoS) attacks poses significant threats to servers globally. Various methods and services have emerged to prevent and mitigate damage caused by these attacks. The challenge in implementing defence lies in timely attack detection, requiring a highly accurate mechanism. DDoS attack methods are diverse and evolving, rendering traditional prevention methods less effective. This research explores the application of machine learning, utilizing the CICDDoS2019 dataset to train hybrid models. The proposed ensemble model combines unsupervised K-Means for dataset labelling and supervised classifiers (Random Forest, XGBoost, AdaBoost, SVM) with Artificial Neural Network (ANN). Achieving an overall accuracy of 99.46%, this study underscores the effectiveness of deep learning in DDoS attack detection.