A user behavior fine classification method and system of a mobile application private encryption protocol

Abstract

The invention discloses a user behavior fine classification method and system of a mobile application private encryption protocol. The method comprises the following steps: 1) collecting the flow of amobile application, and then identifying the private encryption protocol flow from the collected flow according to set private encryption protocol characteristics; 2) collecting flow data of a set user behavior category from the identified private encryption protocol flow, and labeling the flow data; 3) generating a training set, a verification set and a test set according to the flow data collected and marked in the step 2); 4) performing feature extraction on the flow data in the three sets, and converting the flow data into feature vectors; 5) setting hyper-parameters of the selected classifier, and training the selected classifier; 6) verifying the training classifier by utilizing the feature vectors corresponding to the verification set, and 7) classifying the classifier on the testset, and if the set standard is met, classifying the mobile application traffic to be processed by utilizing the classifier.

Description

technical field [0001] The invention relates to a user behavior fine classification method and system of a mobile application private encryption protocol, and belongs to the technical field of computer software. Background technique [0002] With the vigorous development of the Internet, users bring huge profits to enterprises. In the Internet era, the analysis of user behavior helps companies optimize and customize user access to provide better services. It can also be used to build behavior models, distinguish different types of users, and identify malicious and abnormal users. [0003] User behavior classification is a network measurement method based on passively collected traffic. The user behavior classification method can be divided into plaintext protocol traffic and encrypted protocol traffic according to application scenarios. The mainstream solution for user behavior classification of plaintext protocol traffic is to first use deep packet inspection technology (...

AI Technical Summary

Problems solved by technology

The method based on statistical machine learning is the future development trend of processing encrypted traffic, but the current method has problems such as high data set requirements, low universality for samples outside the set, and complicated tuning of the classifier effect.

The existing machine learning methods are mainly used in the identification of websites, which are not refined enough

Images