Abstract: The rapid growth of Internet of Things (IoT) ecosystems has expanded the surface for cyberattacks, especially Distributed Denial-of-Service (DDoS) attacks that threaten critical services. This paper proposes a detection framework that combines Software-Defined Networking (SDN) with machine learning to proactively identify DDoS threats. The system analyzes statistical and behavioral traffic features, using a Support Vector Machine (SVM) classifier for accurate detection. Simulations show over 98% accuracy with low false alarm rates, demonstrating the framework’s reliability and scalability. The paper also reviews related work, outlines the methodology, and discusses future directions.

Keywords: Anomalies, Machine Learning, Threats, Real Time, Mimicking.

| DOI: 10.17148/IARJSET.2025.125364