Private encryption protocol message classification method based on sparse representation and convolutional neural network

Abstract

The invention relates to the technical field of network information, in particular to a private encryption protocol message classification method based on sparse representation and a convolutional neural network, which comprises the following steps: obtaining and preprocessing network traffic data to obtain a data set file and a label file; importing the data set file into a sparse auto-encoder for unsupervised feature learning to obtain input data with smaller dimension; and training the two-dimensional convolutional neural network by using the training set after sparse representation and thetraining set label, performing convolution and pooling, and minimizing errors to obtain a classifier. According to the classification method disclosed by the invention, the classification characteristics of the private encryption protocol message are automatically learned from the original network flow, and classification identification is realized; the method does not depend on the IP address and port number information of the header of the network traffic data packet, and the generalization ability of the classification model is high; sparse representation is used for learning local features of private encryption protocol messages, a two-dimensional convolutional neural network is used for learning global features of the private encryption protocol messages, and the recognition precision of the classifier is improved.

Description

technical field [0001] The invention relates to the field of network information technology, in particular to a private encryption protocol message classification method based on sparse representation and convolutional neural network. Background technique [0002] As the network environment becomes more and more complex, many enterprises and companies use their own private encryption protocol for communication. The private encryption protocol is a protocol standard formulated within the enterprise. The protocol format is not public, and the message data is encrypted. From the perspective of network security and monitoring management, it is necessary to effectively identify private encryption protocol messages. [0003] Traffic classification methods based on port number matching and DPI (Dots Per Inch, Dots Per Inch) based on rule matching need to first parse the message content, and then perform rule matching to achieve classification. These are not suitable for private enc...

AI Technical Summary

Problems solved by technology

Traditional machine learning algorithms have two main problems in classifying private encryption protocol packets: one is that the classified packets need to be manually designed with a feature set that can generally reflect traffic characteristics, and the other is that traditional machine learning methods have great limitations , such as difficult to express complex functions, easy to fall into local optimal solutions, etc.

Due to the above two reasons, the accuracy of traditional machine learning methods for classifying private encryption protocol packets is not very high

Images