A DDOS Attack Traffic Classification Model for Industrial Internet Based on CNN-LSTM
Weixuan Wei, Xianda Liu, Chuan Sheng, Ansong Feng · 2022
With the continuous development and application of industrial Internet, the weakness of the security defense capability of industrial Internet has become increasingly prominent. This paper presents an end-to-end classification model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network for DDoS attacks over industrial Internet. By self-learning the spatial and temporal characteristics of the original attack traffic, the model can avoid subjective errors that may occur due to manual selection of features. This method is a feasible means, with an accuracy rate of 99%.