Method for classifying secondary encrypted traffic transmitted in encrypted channel

Abstract

A method for classifying secondary encrypted traffic transmitted in an encrypted channel relates to the technical field of network information security, and comprises the following steps: firstly, collecting positive and negative samples, converting an encrypted load in sample data into an rgb image, training a deep neural network backbone network model by using the rgb image, and identifying theinternet surfing behavior in the real-time network flow data and the internet surfing program combination adopted by the internet surfing behavior by using the deep neural network backbone network model. According to the method provided by the invention, the classification of the Internet surfing behaviors in the network flow data and the Internet surfing program combinations adopted by the Internet surfing behaviors can be accurately realized.

Description

technical field [0001] The invention relates to the field of physics, in particular to network information technology, in particular to a method for classifying secondary encrypted traffic transmitted in an encrypted channel. Background technique [0002] With the popularization of personal mobile terminals, a wide variety of mobile Internet applications have generated a large amount of traffic, and with the widespread use of HTTPS-like encrypted transmission protocols, the encrypted traffic loads generated by these mobile Internet applications have been difficult to break easily, and With the improvement of personal privacy awareness, more users will choose encrypted channels such as VPN to access the Internet to hide their online behavior, which will have a negative impact on network security. How to efficiently identify the user's online behavior from the intercepted twice-encrypted traffic has become a research hotspot in recent years. [0003] Among the traditional met...

AI Technical Summary

Problems solved by technology

However, with the use of technologies such as port forgery, plaintext encryption, and secondary encryption, the above classification methods cannot meet the classification accuracy requirements at this stage.