Detection Of DDOS Attack Using Machine Learning

The Distributed Denial-of-Service (DDoS) attack is one of the most dangerous cyber threats, surpassing traditional Denial-of-Service (DoS) attacks due to its distributed nature, where multiple hosts collectively target a system, rendering its services inaccessible. Addressing this challenge requires an advanced and reliable detection mechanism. This research presents a machine learning-based approach for DDoS attack detection using Logistic Regression, Random Forest, and Neural Network classifiers. The proposed model is trained on a cleaned and pre-processed dataset with feature scaling to enhance model performance. A Flask-based web application deploys these models, enabling real-time prediction through a user-friendly interface. The trained models are evaluated using key metrics such as accuracy, F1-score, precision, recall, and confusion matrix. Comparative analysis reveals the strengths of ensemble-based methods, offering a scalable and robust solution for mitigating DDoS attacks in real-world environments.