Machine Learning Detection of DDoS Attacks Based on Visualization of Recurrence Plots
Lyudmyla Kirichenko, Petro Zinchenko, Тамара Радівілова, Maksym Tawalbeh · 2020
The article considers a new method of detecting DDoS attacks based on the construction of recurrence plots. Time traffic realization is transformed into a matrix consisting of 0 and 1, which characterizes the recurrence of the re- alization. The matrix is presented in the form of a black-and-white image. Then the residual neural network is used to classify images. This approach is used to detect the realizations of the attacked network traffic. The results showed that the proposed method has a sufficiently high accuracy of classification and can be used to detect attacks in intrusion detection systems.