Classification Methods of Machine Learning to Detect DDoS Attacks

In this paper the problem of intrusion detection by classification of the network traffic realizations was considered. The Machine Learning methods using fractal and recurrence features are applied to solve this problem. The simulated traffic realizations and the experimental data sets that contain attacks realization were used. The numerical experiment to detect intrusions using the example of detecting typical DDoS attacks was conducted. It has been shown that the classification by Random Forest method can effectively detect attacks in network traffic.