Study On Static Detection Method For Android Malicious Application

With the rapid development of the Internet,mobile intelligent terminal are becoming more and more popular,and android is most popular.According to the statistics,android has occupied more than 80% of the market.However,it also attracts a lot of malicious developers whose try to continuously upload malicious application in Google,anzhi and other official markets to steal uses' privacy and gain benefits.Therefore,the research of malware detection method for mobile intelligent terminal has attracted more and more scholars at home and abroad.This paper mainly focuses on android malware detection methods.Firstly,the paper introduces the development trend of android software,the android system architecture and the four components of the structure described in detail.After that,it analyzes the android malware threats,and details analysis of the android security protection mechanism,and targets the analysis of the existence of the signature mechanism and the authority mechanism may be a security threat.Lastly,the android malicious software static detection methods are described and introduced with their basic principles and advantages and disadvantages.In order to further improve the detection accuracy and reduce the detection of false positives,we propose a new malware detection method based APK Signature of information feedback in this paper.Based on SVM classification algorithm,our proposed method of eigenvalue extraction adopts heuristic rule learning to sig APK information verify screening,and it also implements the heuristic feedback,and so on,from which achieve the purpose of more accurate detection of malicious application.Otherwise,this method introduces the APK signature detection preprocessing screening process,and describes in detail how the heuristic method is applied to the classification of Android malware,and gives the acquisition method of the rule base.Finally,the SigFeedback detection algorithm overcomes the high false positives problems by filtering preprocessing,and obtains the new rule through heuristic to realize the high detection rate.The results show that the SigFeedback algorithm has high efficiency,making the rate of false positive from 13% down to 3% and the rate of detection from 91% up to 96%.