Enhancing DDoS Attack Detection: Leveraging Decision Tree Machine Learning Model for Real-Time Monitoring and Adaptive Threat Identification

Abstract

The traditional detection methods are insufficient to address Distributed Denial of Service (DDoS) threats accurately and promptly because of their increased occurrence frequency and complexity. The implementation of Decision Tree models succeeded in developing attack detection strategies against DDoS attacks at higher accuracy levels than SVM and Random Forest models. The system operates through continuous monitoring which allows adaptive gearing and scaling multiple times to perform real-time network traffic analysis for emerging threat detection. The Decision Tree model helps the system to detect attacks better while lowering false alerts while enabling an efficient DDoS security system than traditional methods. The defensive capabilities of network security dramatically improve because of attack and dynamical proactive measures applied to face evolving DDoS threats.