Abstract
As Distributed Denial of Service (DDoS) attacks evolve, accurately detecting these threats becomes essential to ensuring network stability. Traditional methods often face challenges in recognizing adaptive DDoS patterns and balancing detection accuracy with false positives. This paper presents a machine learning-based framework leveraging Gaussian Naive Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and an Ensemble Random Forest classifier. Through an in-depth performance analysis using accuracy and AUC-ROC metrics, the hybrid model aims to provide a robust, scalable solution to enhance network security.