Machine Learning for Distributed Denial of Service Attack Detection in Software-defined IoT

The implementation of Software-defined networking in the Internet of Things is an approach to address standardization challenges. However, the SDN centralized architecture along with the IoT resource constraints, turn these networks prone to DoS and DDoS attacks. State-of-the-art is divided in complex DoS and DDoS detection methods with high detection performance, but implementation issues, and less complex methods, which compromise detection performance. In this work, we use classic machine learning schemes to operate in resource-constrained SD-IoT environments without increasing perception layer requirements. Results show that Random Forest outperforms state-of-the-art methods in its detection rate and detection time, while using only two network performance metrics as input data.