A mobile application apk file embedded privacy policy extraction method

Abstract

The invention discloses a method for extracting a privacy policy embedded in an APK file of a mobile application, which belongs to the field of analysis and detection of Android mobile terminal application software. Crawl the content of each webpage and extract the feature words in the privacy policy text. At the same time, collect the characteristic words of several web pages to train the binary classification model in advance; input each characteristic word of the APK file to be detected into the trained binary classification model one by one, and judge whether there is a privacy policy page in the output result, and if so, output the privacy policy And end; otherwise, conduct automated dynamic testing, extract the corresponding URL links by monitoring the request address in the traffic, crawl the content of each page to extract feature words, and enter the binary classification model to judge until the privacy policy page is found or exceeds the set value End of traversal depth. The invention improves the extraction efficiency and success rate of the privacy policy through the combination of dynamic and static tests.

Description

technical field [0001] The invention belongs to the field of analysis and detection of Android mobile terminal application software, and relates to a method for extracting a privacy policy embedded in an APK file of a mobile application. Background technique [0002] Static analysis refers to a technology that uses various means such as lexical analysis or syntax analysis to scan program files without running them, thereby generating decompiled code of the program, and then reading the decompiled code to grasp the function of the program. It is essentially a static text analysis, so it has high analysis efficiency. [0003] Common static decompilation tools include apktool, backsmali, and dex2jar, among which apktool is the most commonly used decompilation tool for static analysis. It is written in Java and can decompile and recompile APK files. It also has the installation-specific framework-res framework. Functions such as cleaning up the last decompiled folder. [0004]...

AI Technical Summary

Problems solved by technology

[0008] However, there are few existing studies on the extraction of privacy policies embedded in mobile applications. The main method is to analyze the application file structure through static analysis, preprocess the input samples, extract the required information, and generate the Activity tree. Figure; and then based on the Activity tree diagram and tree hierarchy, the Activity traversal script written by the traversal strategy, the main task is to find the page where the privacy agreement is located, and obtain the privacy policy file inside the mobile application by matching the keywords of the page-related control text

[0009] Since the accuracy of the activity tree diagram decreases with the level, and there may be omissions in the judgment of the privacy policy link based on the control text matching, there is still room for improvement in the success rate of privacy policy discovery

In addition, this method requires two steps of static analysis and automated testing for each input sample. Due to the complexity of the steps and the time-consuming automated testing, the extraction speed is slow

Images