An Android application network behavior classification method and system based on deep learning

A technology of application network and deep learning, which is applied in the Android application network behavior classification method and system field, can solve the problems of encrypted data packet classification, incomplete collection of data packets, etc., achieve high accuracy, reduce orders of magnitude, and facilitate training and learning effect

Inactive Publication Date: 2019-03-08
NANJING UNIV OF SCI & TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a deep learning-based Android application network behavior classification method to solve the problem of incomplete collection of data packets and the inability to classify encrypted data packets in existing classification methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Android application network behavior classification method and system based on deep learning
  • An Android application network behavior classification method and system based on deep learning
  • An Android application network behavior classification method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Such as figure 1 As shown, a deep learning-based Android application network behavior classification method, the specific steps are:

[0039] Step 1, such as figure 2 As shown in the figure, construct a custom event execution sequence combination and drive the Android application to run, and obtain the dynamic network behavior data packet of the Android application. The specific steps are:

[0040] Step 1-1. Obtain N Android application APKs.

[0041]Step 1-2: Model and analyze the Android application, use a decompilation tool to decompile the Android application, analyze the decompiled code, and obtain all the entry functions of the application about network behavior, that is, the program runs start point. Traversing the calling statements in the entire APK, saving the location of the method calling to generate a list to be analyzed. Generate forward and reverse function call graphs according to the call relationship between functions, and use the soot tool to gen...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an Android application network behavior classification method and system based on deep learning, and the method comprises the steps of firstly constructing a user-defined eventexecution sequence combination, driving an Android application to operate, and obtaining a dynamic network behavior data packet of the Android application; bicycling, preprocessing the dynamic behavior data packet of the Android application obtained in the step 1, and converting binary data transmitted in the network into a gray value so as to convert the data packet into a gray image; then constructing a convolutional neural network classification model; and finally converting the preprocessed grayscale image into a matrix vector, and inputting the matrix vector into a convolutional neural network classification model for learning to obtain a classification model of the Android application sample. According to the present invention, the Android application classification problem is converted into the image classification problem, the features are learned by using the multilayer convolutional neural network, and the accuracy is higher.

Description

technical field [0001] The invention belongs to the technical field of Android mobile terminal software security, in particular to a method and system for classifying Android application network behaviors based on deep learning. Background technique [0002] In recent years, with the continuous popularization of Android smart terminals, the number of Android mobile phone applications has also increased exponentially, providing people with various types of services. However, the growth in the number of these applications also complicates the security and management of mobile networks, making it challenging and time-consuming to keep up with the new applications that appear every day. Moreover, QoS management for applications is becoming more and more important at present. Qos is a security mechanism of the network and a network technology used to solve problems such as network delay and congestion. Qos requires service providers to use various network technologies to provide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06F21/56
CPCG06F21/563G06N3/045G06F18/24G06F18/214
Inventor 俞研唐军付安民苏铓徐安孟
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products