Prediction of DDoS Flooding Attack using Machine Learning Models

Nowadays multifarious types of Distributed Denial of Services attacks occur owing to the rapid growth in technology and also potentially cause harm in Software Defined Network architecture. As a consequence, it is found one among the crucial and commonly occurring cyber-attack. There are many traditional and advanced methods for detecting these attacks. This paper intends to build a Machine Learning based model for predicting the DDoS Flooding attacks. The DDoS flooding attacks to be anticipated are involved with numerous types. The ML models used to classify these attacks are namely, Logistic Regression, K-nearest neighbour, Multi-Layer Perceptron, and, Decision Tree classifiers. The implementation is been done with a jupyter notebook with required python packages installed. Among these four classifiers, KNN and Decision Tree Classifiers have shown almost similar and best accuracy of 99.98 percent in TCP and ICMP flooding attack prediction. The Decision Tree Classifier has shown the best accuracy of 77.23 percent compared to others in UDP flooding attack prediction.