Unlock instant, AI-driven research and patent intelligence for your innovation.

Android software dynamic analysis and detection method based on behavior feature extraction

A technology of feature extraction and detection method, which is applied in the direction of computer security devices, instruments, calculations, etc., can solve the problems of irreversible steps and high requirements for testers, and achieve the effect of saving time, shortening inspection time, and reducing requirements

Active Publication Date: 2022-06-17
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition to the shortcomings of the static and dynamic analysis methods, the comprehensive analysis method also has some disadvantages, including the steps of dynamic and static analysis cannot be reversed, and the analysis results need to be integrated and analyzed, and the requirements for testers are higher.

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
  • Android software dynamic analysis and detection method based on behavior feature extraction
  • Android software dynamic analysis and detection method based on behavior feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Explanations of terms involved in the present invention include:

[0045]Behavioral feature extraction: Monitor the execution process of Android apps, and record the sequence and logical relationship of Android app behaviors, so as to bind one or more behavioral features to Android apps.

[0046] The present invention is based on the dynamic analysis and detection method of Android software based on behavior feature extraction. When the Android app software to be tested is dynamically running, the behavior between each execution module is recorded, and the test case is exported to the Android execution simulator according to the analysis result of the behavior feature. After the simulator is executed, the execution result is recorded, and the corresponding behavior characteristics and corresponding execution results are used to determine whether the software has vulnerabilities and malicious behaviors.

[0047] The detection process of the present invention is as follow...

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 relates to a dynamic analysis and detection method for Android software based on behavior feature extraction. When the Android app software to be tested is dynamically running, the behavior between execution modules is recorded, and then the behavior log is analyzed according to the feature extraction method to obtain behavior characteristics. According to the analysis results of behavioral characteristics, export test cases to the Android execution simulator, and record the execution results after execution through the simulator, and judge whether the software has loopholes and malicious behaviors through the corresponding behavioral characteristics and corresponding execution results. This solves the problems of the existing analysis methods, such as the high rate of false alarms in static analysis, high pressure on the system and high requirements for personnel in dynamic analysis, the step-by-step analysis of dynamic-static combined analysis, long test time, and steps that cannot be reversed.

Description

technical field [0001] The invention relates to a dynamic analysis and detection method of Android software, in particular to a dynamic analysis and detection method of Android software based on behavior feature extraction, and belongs to the technical field of mobile communication security. Background technique [0002] With the rapid development of society, more and more people are relying on the Internet to obtain the information they need. At the same time, people no longer rely entirely on personal computers to perform some Internet operations, such as smartphones and tablet computers. Mobile Internet devices are becoming a convenient channel for people to connect to the Internet and obtain information anytime, anywhere. [0003] The openness of the network and the open source of the Android system make Android software on the Internet the preferred target of malicious attacks. The number of users connecting to the Internet through mobile terminals is increasing day by ...

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 Patents(China)
IPC IPC(8): G06F21/56
CPCG06F21/566
Inventor 孙知信叶萌宫婧
Owner NANJING UNIV OF POSTS & TELECOMM