A method and system for classifying Android malicious applications based on behavioral characteristics
A malicious application and classification method technology, applied in the field of Android malicious application classification method and system, can solve the problems of low feasibility, serious time consumption, increase dynamic analysis time consumption, etc., and achieve the effect of reducing time and efficiency and improving accuracy.
Active Publication Date: 2021-04-13
SOUTH CHINA NORMAL UNIVERSITY +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Taking Anubis as an example, it can ensure program coverage in a coarse-grained manner, but the time consumption is very serious
For a large number of APP-targeted demands, the feasibility is relatively low
At the same time, with the growth of malicious types and the increase of checkpoints, the consumption of dynamic analysis time will also be increased
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0089] Aiming at the problem that the existing technology cannot minimize the classification time while ensuring the correct rate of classification of malicious applications, the present invention proposes a new method and system for classifying Android malicious applications based on behavioral characteristics, which ensures correct classification of malicious applications In the case of high rate, the time consumption of malicious application detection is greatly reduced.
[0090] The entire Android malicious application detection or classification process of the present invention will be described in detail below from the two aspects of nomenclature explanation and specific implementation process.
[0091] (1) Name Explanation:
[0092] The proper nouns that the present invention relates to are as follows:
[0093] SVM (Support Vector Machine): support vector. In the field of machine learning, support vector machine (SVM) is a supervised learning model, usually used for p...
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
Login to View More Abstract
The invention discloses a method and system for classifying Android malicious applications based on behavioral characteristics. The method includes: decompiling input Android application samples to obtain decompiled source files; performing grammatical analysis and analysis on the decompiled source files. Feature extraction to obtain static and behavioral features of Android malicious applications; use support vector machine classifier to classify Android applications to be classified according to the obtained static features and behavioral features, so as to classify Android applications to be classified as Android malicious applications or Android non-malicious applications application. The system includes a decompilation module, a syntax analysis and feature extraction module, and a classification module. The present invention introduces behavioral features with semantics, and comprehensively applies static analysis method, semantic analysis method and support vector machine classification method to classify Android malicious applications, which not only reduces the time and efficiency of Android malicious application classification, but also improves Android malicious applications. classification accuracy. The invention can be widely used in the field of data mining.
Description
technical field [0001] The invention relates to the field of data mining, in particular to a method and system for classifying Android malicious applications based on behavioral characteristics. Background technique [0002] In recent years, with the rapid development of mobile hardware devices and software, mobile phone platforms have rapidly become popular in people's lives. The rapid development of the mobile Internet has led to a sharp increase in the number of smartphones, and the number of mobile phone users, Android application levels, and market size have all shown explosive growth trends. The rapid growth of mobile Internet users such as mobile phones and ipads has promoted market development. According to the statistics of iResearch, an authoritative third-party consulting platform in China, in 2012, the total number of Internet users in China was 560 million, the number of Internet users on mobile terminals was 420 million, and the penetration rate of Internet us...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/56G06F8/53G06K9/62
CPCG06F8/53G06F21/563G06F2221/033G06F18/2411
Inventor 赵淦森陈梓豪梁轼文刘全凤朱健飞吴杰超任雪琦王欣明张奇支杨晋吉叶卫东温赞亮黄永聪
Owner SOUTH CHINA NORMAL UNIVERSITY