Method for detecting abnormal user of communication network based on generated confrontation network

Abstract

The invention discloses a method for detecting an abnormal user of a communication network based on a generated confrontation network. The method comprises the following steps: firstly regularizing the data of the abnormal user to obtain data with consistent same dimension and magnitude; training the generated confrontation network, that is, training a generator and a discriminator, to achieve oversampling of the abnormal user; and forming a training data set via the data generated by the generator and a normal user, classifying the training data set by using a deep fully connected neural network, and judging a user type. By adoption of the method disclosed by the invention, by means of a mutual game training mode between the neural networks in the generated confrontation network, the approximation of the data distribution of the abnormal user is achieved, the detection of the abnormal user is achieved, and the technical problem that the proportional imbalance of the training data setaffects the training effect of a classification model is solved.

Description

technical field [0001] The invention belongs to the field of detecting abnormal users of communication networks, and in particular relates to a method for detecting abnormal users of communication networks based on generative confrontation networks. Background technique [0002] Due to the openness of wireless channels, with the development of wireless communication technology, there are more and more security problems. If there is no effective response strategy, it may cause immeasurable losses to wireless communication networks and legitimate users. Non-orthogonal multiple access (NOMA) technology has become one of the key technologies of the next generation mobile communication system (5G). With the development of NOMA, security issues in NOMA have also begun to receive attention and research. In the power domain NOMA, a corresponding power allocation scheme is derived based on the user's channel state information (Channel State Information, CSI), and superimposed infor...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to realize the efficient combination of different attack models against malicious users, propose a communication network abnormal user detection method based on generative confrontation network, realize abnormal user detection, and solve the problem that the unbalanced proportion of training data set affects the training effect of classification model technical problem

Images