Software Defined Networking (SDN) offers a flexible and programmable alternative to traditional network architectures by decoupling the control and data planes and introducing a centralized controller and application layer. While this architecture enables dynamic traffic management, centralized policy enforcement, and seamless integration of network services, it also introduces critical vulnerabilities, particularly to Distributed Denial-of-Service (DDoS) attacks. The centralized nature of the SDN controller makes it a prime target, where resource exhaustion or flow table saturation can lead to widespread service disruption. These attacks can severely impact time-sensitive applications and compromise the overall stability of the network. In this work, an AI-driven framework is proposed for detecting and mitigating DDoS attacks in SDN environments. The framework incorporates models from diverse categories, including meta-learning, adaptive reinforcement learning, supervised learning, unsupervised clustering, and deep learning techniques. This broad integration enables a comprehensive evaluation of detection capabilities and ensures adaptability to various traffic patterns and attack scenarios. A hybrid Particle Swarm Optimization Genetic Algorithm (PSO-GA) approach is also presented to fine-tune models’ parameters and thereby enhance the detection efficiency of the models. Extensive experiments are conducted using multiple performance metrics to evaluate each model under both optimized and non-optimized conditions. The results demonstrate the effectiveness of the proposed framework in enhancing SDN resilience against DDoS threats.
Al-Jabri et al. (Tue,) studied this question.