SDN-based detection and mitigation of botnet traffic in large-scale networks

The proliferation of botnets poses a severe threat to the stability and security of large-scale network infrastructures. Traditional detection and mitigation approaches often lack the agility and scalability required to respond effectively to dynamic and sophisticated botnet behaviors. This paper proposes a novel framework leveraging Software-Defined Networking (SDN) for the real-time detection and mitigation of botnet traffic in expansive network environments. By decoupling the control and data planes, SDN enables centralized visibility and programmable control, which are essential for adaptive threat response. The proposed system integrates machine learning-based flow analysis with SDN controller policies to classify and block malicious traffic patterns. A simulated testbed using flow-level datasets was deployed to evaluate detection accuracy, response latency, and overall network performance. Results indicate a significant improvement in detection rates, reduced false positives, and efficient policy enforcement across varying network loads. The study contributes to advancing scalable and intelligent network defense mechanisms and underscores the potential of SDN as a strategic enabler in next-generation cybersecurity frameworks.