Online alert system for DDoS attack detection and prevention using machine learning classification algorithms

Distributed Denial of Service (DDoS) attack makes a server inaccessible by flooding it with fallacious traffic. It uses many intermediate devices such as computers, servers, smartphones, and even IoT Devices to generate false traffic. These attacks become more threatening if the attackers use any of these devices to have access to WiFi routers, security cameras, smart devices, etc. This paper proposes a model for DDoS attack detection and mitigation that identifies the DDoS attack and alerts the administrative authorities with the help of machine learning classification algorithms. The paper surveys discrete types of Machine Learning algorithms to identify and mitigate the DDoS attack. Three labeled datasets are employed in this paper to train the model for effective DDOS attack detection with better accuracy. These data sets comprises of benign and malignant attacks to train and test the classification algorithms. Based on the experimental results and performance metrics, it is identified that the XGBoost algorithm provided better accuracy of 99.8% on all three labeled datasets.