Distributed Denial-of-Service (DDoS) Attack Detection using 1D Convolution Neural Network (CNN) and Decision Tree Model

Abstract

The major problem of internet security is a Distributed Denial-of-Service (DDoS) attack, which can’t be detected easily. This attack is said to have occurred when lots of service requests are simultaneously received at a server on the internet. This makes the server too busy to provide normal services for others. The Distributed Denial of Service (DDoS) attacks nature on large networks on the Internet demanding to develop the effective detection and response methods. The deployment of these technique should perform not only at the network core but also at the edge. A DDoS attack detection framework is presented based on transfer learning model consisting of 1D Convolution Neural Network (CNN) and decision tree classifier. The 1D CNN model utilizes for features extraction from the input network traffic data. This operation also reduces the dimension of the data thereby removing the redundancy in the data. These features are given to the decision tree model for classification. The proposed framework identified the DDoS attacks with good accuracy. This system could identify attacks in real-time and provide network security.