Classification and Prediction of Distributed Denial of Service Attacks using Random Forest and a Comparative Analysis of Machine Learning Algorithms

Hackers or cybercriminals utilize DDoS (Distributed Denial of Service) attacks, a type of malicious cyber-attack, to render an online service, network resource, or host system inaccessible to its intended users on the Internet. The proposed system forecasts DDoS attacks using random forest, and we also compared four different classification techniques. The Random Forest, Logistic Regression, Support Vector Classifier, K-Nearest Neighbors, and Decision Tree algorithms are the machine learning models on which this project is based. Python was utilized as a simulator and the DDoS dataset was used to achieve the proposed goal. In order to identify the model performance after applying the machine learning methods, we built a confusion matrix.