Software-defined networking (SDN) has emerged in recent years as a form of Internet architecture. Its scalability, dynamics, and programmability simplify the traditional Internet structure. This architecture realizes centralized management by separating the control plane and the data-forwarding plane of the network. However, due to this feature, SDN is more vulnerable to attacks than traditional networks and can cause the entire network to collapse. DDoS attacks, also known as distributed denial-of-service attacks, are the most aggressive of all attacks. These attacks generate many packets (or requests) and ultimately overwhelm the target system, causing it to crash. In this article, we designed a hybrid neural network DDosTC structure, combining efficient and scalable transformers and a convolutional neural network (CNN) to detect distributed denial-of-service (DDoS) attacks on SDN, tested on the latest dataset, CICDDoS2019. For better verification, several experiments were conducted by dividing the dataset and comparisons were made with the latest deep learning detection algorithm applied in the field of DDoS intrusion detection. The experimental results show that the average AUC of DDosTC is 2.52% higher than the current optimal model and that DDosTC is more successful than the current optimal model in terms of average accuracy, average recall, and F1 score.
Long-Memory Dependence Statistical Models for DDoS Attacks Detection
