本文選題：Android + 惡意程序��； 參考：《電子科技大學(xué)》2016年碩士論文

【摘要】：近年來(lái),隨著移動(dòng)互聯(lián)網(wǎng)的飛速發(fā)展,智能終端設(shè)備得到廣泛的普及,尤其是Android系統(tǒng)已經(jīng)成為移動(dòng)市場(chǎng)份額第一的操作系統(tǒng)。Android系統(tǒng)給人們帶來(lái)極大便利的同時(shí),也帶來(lái)了極大的安全隱患。這是由于Android系統(tǒng)安全模型和權(quán)限模型具有很大的開放性,一些移動(dòng)應(yīng)用市場(chǎng)對(duì)用戶上傳的APP缺乏有效的審核以及移動(dòng)用戶本身比較缺乏相應(yīng)的安全意識(shí)及知識(shí),從而Android系統(tǒng)很容易成為黑客的攻擊對(duì)象,其惡意行為包括:信息竊取、惡意扣費(fèi)、資費(fèi)消耗、系統(tǒng)破壞、遠(yuǎn)程控制、誘騙欺詐,惡意傳播,流氓行為等。因此,面對(duì)日益龐雜的移動(dòng)應(yīng)用程序庫(kù),如何有效的組織,管理及檢測(cè)已經(jīng)成為亟待解決的問(wèn)題。本文選取Android平臺(tái)的應(yīng)用程序作為研究對(duì)象,主要研究了Android平臺(tái)的安全架構(gòu)及惡意程序分析檢測(cè)技術(shù)。其中,針對(duì)Android平臺(tái)的安全架構(gòu)主要研究了Linux內(nèi)核層的安全機(jī)制及Android系統(tǒng)特有的一些安全機(jī)制,如進(jìn)程沙箱隔離,權(quán)限控制,以及進(jìn)程通信等,并特別針對(duì)惡意程序的分類和運(yùn)行機(jī)制進(jìn)行了詳細(xì)研究;針對(duì)惡意程序分析檢測(cè)技術(shù),主要研究和分析了靜態(tài)分析技術(shù)和動(dòng)態(tài)分析技術(shù)的基本特征、優(yōu)缺點(diǎn),并以此為基礎(chǔ),給出了適用于Android平臺(tái)的惡意程序檢測(cè)方案,包括惡意程序樣本分析,惡意行為特征提取,基于惡意行為特征的惡意程序檢測(cè)模型,并進(jìn)行了實(shí)驗(yàn)驗(yàn)證;設(shè)計(jì)和實(shí)現(xiàn)惡意程序檢測(cè)原型系統(tǒng)。另外,本文還對(duì)應(yīng)用程序運(yùn)用了靜態(tài)分析與動(dòng)態(tài)分析相結(jié)合的方式提取特征,基于機(jī)器學(xué)習(xí)理論方法,提出了三層混合系統(tǒng)算法來(lái)對(duì)安卓app進(jìn)行分類;最后將對(duì)本方案的查殺效果進(jìn)行數(shù)據(jù)和試驗(yàn)分析,實(shí)驗(yàn)結(jié)果表明本模型具有很好的準(zhǔn)確性,并且具有較低的誤報(bào)率和漏報(bào)率。
[Abstract]:In recent years, with the rapid development of mobile Internet, intelligent terminal equipment has been widely popularized, especially the Android system has become the first operating system of mobile market.Android system to bring great convenience to people, but also brings great security risks. This is due to the security model and authority model of the Android system. It is very open, and some mobile applications lack the effective audit of the APP uploaded by the user and the mobile users lack the corresponding security awareness and knowledge. Thus the Android system is easy to be a hacker's attack object. Its malicious behavior includes information theft, malicious buckle, cost consumption, system destruction, remote control. In the face of increasingly complex mobile application library, how to organize, manage and detect effectively has become an urgent problem. This paper selects the application program of the Android platform as the research object, mainly studies the security architecture of the Android platform and the analysis and detection techniques of malicious programs. For the security architecture of the Android platform, the security mechanism of the Linux kernel layer and the specific security mechanisms of the Android system are mainly studied, such as process sandbox isolation, authority control, and process communication, especially for the classification and operation mechanism of malicious programs, and the malware analysis and detection technology is applied to the malicious program. In this paper, the basic characteristics and advantages and disadvantages of static analysis technology and dynamic analysis technology are mainly studied and analyzed. On the basis of this, a malicious program detection scheme suitable for Android platform is given, including sample analysis of malware, feature extraction of malicious behavior, malware detection model based on malicious line, and experimental test. In addition, this paper also uses a combination of static analysis and dynamic analysis to extract the characteristics of the application. Based on the theory of machine learning, a three layer hybrid system algorithm is proposed to classify the Android app. The experimental results show that the model has good accuracy and low false positive rate and false negative rate.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP316;TP309

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 文偉平;梅瑞;寧戈;汪亮亮;;Android惡意軟件檢測(cè)技術(shù)分析和應(yīng)用研究[J];通信學(xué)報(bào);2014年08期

2 焦四輩;應(yīng)凌云;楊軼;程瑤;蘇璞睿;馮登國(guó);;一種抗混淆的大規(guī)模Android應(yīng)用相似性檢測(cè)方法[J];計(jì)算機(jī)研究與發(fā)展;2014年07期

3 沈才j;唐科萍;俞立峰;樊甫偉;;Android權(quán)限提升漏洞攻擊的檢測(cè)[J];電信科學(xué);2012年05期

4 祁昌平;孫克雷;;計(jì)算機(jī)病毒及其防范策略研究[J];電腦學(xué)習(xí);2009年04期

5 厲小潤(rùn);趙光宙;趙遼英;;決策樹支持向量機(jī)多分類器設(shè)計(jì)的向量投影法[J];控制與決策;2008年07期

6 張學(xué)工;關(guān)于統(tǒng)計(jì)學(xué)習(xí)理論與支持向量機(jī)[J];自動(dòng)化學(xué)報(bào);2000年01期

，

本文編號(hào)：1908081