Smart-IoT: a DDoS protection system for the Internet of Things
Network Security, IoT, DDoS, Machine Learning, SDN
The increase in the number of networked devices in the context of the Internet of Things (IoT) has driven the number of Distributed Denial of Service (DDoS) attacks in recent years. This threat takes advantage of the security limitations of these devices and their geographic locations to leverage the impact of the attacks. Developing mechanisms to detect and mitigate DDoS attacks in this new paradigm is a current challenge in network security. This work proposes a defense mechanism integrated into the IoT network controller that uses Machine Learning (AM) techniques to detect these attacks and the flexibility of Software-Defined Networks (SDN) for their mitigation. The proposed system uses random samples to perform network traffic classification and the OpenFlow (OF) protocol to apply real-time mitigation measures. The solution was tested with four recent datasets in a controlled laboratory environment, showing to detect and mitigate DDoS attacks, with a high hit rate and low false alarm rate.