A DDoS attack detection algorithm based on improved grid search to optimize SVM in SDN environment
Meigen Huang, Boqi Zhao · 2023
Software defined network has proposed a new architecture idea, but the controller is vulnerable to distributed denial of service attacks, resulting in a single point of failure. This paper proposes a DDoS attack detection algorithm based on improved grid search optimization SVM in SDN environment. Firstly, according to the characteristics of DDoS attacks and information of flow table items, the most relevant six-dimensional features are selected, then use the improved grid search algorithm to calculate the optimal penalty coefficient and kernel function parameters of SVM model, finally use SVM algorithm to detect DDoS attacks and improve the performance of intrusion detection algorithm. The experimental results in the same scene show that the improved SVM has higher detection rate and recall rate than the SVM algorithm.