Digital Twin-based DDoS Attack Detection Using Software Defined Networks

The concept of Digital Twin (DT) has transformed industries by enabling virtual replicas of physical systems for monitoring and optimization. Integrating DT with Software-Defined Networks (SDN) enhances network flexibility, scalability, and security. This paper presents an SDN-driven digital twin framework for real-time network simulation and cybersecurity enhancement, particularly for Distributed Denial of Service (DDoS) attack mitigation. The system employs Machine Learning (ML) techniques, such as Random Forest, to predict network behavior and dynamically respond to threats. The proposed approach is validated in a simulated environment, demonstrating improved threat detection and adaptive response mechanisms. The study emphasizes how digital twins provide deeper insights into traffic anomalies and attack patterns, thereby optimizing security strategies in an evolving cyber-threat landscape