DDOS Attack Classifier Using Machine Learning

The increasing frequency and complexity of Distributed Denial of Service (DDoS) attacks present substantial challenges to network security. Traditional Intrusion Detection Systems (IDS) often struggle to detect intricate attack patterns in real-time. This research introduces a machine learning-based classifier designed to accurately identify and classify DDoS attacks. Leveraging the Intrusion Detection Evaluation Dataset (CIC-IDS2017), which contains realistic and labeled network traffic, we assess multiple models—Random Forest, Logistic Regression, Gradient Boosting, and Naive Bayes. By incorporating advanced feature selection and hyperparameter tuning, this classifier effectively minimizes false positives and demonstrates strong performance across metrics like accuracy, precision, and recall, making it a promising candidate for real-time DDoS detection in modern networks.