Detection of DDOS Attacks using Ensemble and Probabilistic Classifiers

Distributed Denial of Service (DDoS) attacks disrupt online services, leading to operational and financial losses. This project presents a machine learning-based detection system utilizing Logistic Regression, Decision Tree, Random Forest, and Gaussian Naive Bayes to analyze network traffic and identify anomalies. By employing data preprocessing and extracting critical features, the system enhances accuracy and efficiency in distinguishing between normal and malicious traffic. Each algorithm is evaluated based on performance, scalability, and computational efficiency. Future enhancements will focus on real-time monitoring and the exploration of more advanced models to improve detection capabilities.