Network intrusion detection method based on generative adversarial network oversampling

Abstract

The invention discloses a network intrusion detection method based on generative adversarial network oversampling, and the method comprises the steps: selecting main features in a network intrusion detection data set, carrying out the data preprocessing of the main features, obtaining a training set, and carrying out the oversampling of unbalanced data in the training set through a CGAN model; then inputting the data into the network intrusion detection model for training, and testing the network intrusion detection model by using the test set after the training is completed. According to the method, the detection model is trained after the problem of data imbalance is solved through the oversampling samples generated by the CGAN model, so that the detection model classifies the classes with a small number of samples more accurately, and the overall accuracy of the detection model is improved.

Description

technical field [0001] The invention belongs to the technical field of network security, and more specifically relates to a network intrusion detection method based on over-sampling of generative confrontation network. Background technique [0002] With the rapid development of computer technology and frequent occurrence of network attacks, more and more researchers have devoted themselves to the research of network intrusion detection models. Network intrusion detection refers to monitoring abnormal network traffic and activities and distinguishing them from normal expected network behaviors. The detection accuracy of the detection model in practical applications is highly dependent on the dataset used to train the model. In practical applications, since network intrusions do not occur all the time, the number of abnormal samples is usually far less than normal samples when capturing data samples, resulting in data imbalance in most network intrusion detection datasets. q...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a network intrusion detection method based on generative adversarial network oversampling, through the oversampling samples generated by the CGAN model, first solve the problem of data imbalance and then train the detection model, so that the detection model The classification of categories with a small number of samples is more accurate, thereby improving the overall accuracy of the detection model

Images