Android Malware Detection and Classification through Permission Based Analysis using SVM

DC Field Value Language
dc.contributor.advisorYoung-June Choi-
dc.contributor.authorDebelo, Bemnet Aberra-
dc.date.accessioned2018-11-08T08:04:28Z-
dc.date.available2018-11-08T08:04:28Z-
dc.date.issued2013-08-
dc.identifier.other15053-
dc.identifier.urihttps://dspace.ajou.ac.kr/handle/2018.oak/10146-
dc.description학위논문(석사)아주대학교 일반대학원 :컴퓨터공학과,2013. 8-
dc.description.abstractIn the past few years, smartphones popularity has grown exponentially. This has led to the equivalent growth in their related attacks and vulnerability exploitations. Especially, Android, one of the prominent smartphone operating system has contributed to the highest market share since its release in 2008. It is reported that malwares targeting Google’s Android platform has increased nearly six-fold in the third quarter of 2012. In this thesis project, we propose Sandroid; a malware detection and classification framework based on support vector machines (SVM) using extracted features from the AndroidManifest file. The SVM vector construction uses distinct features such as sets of critical permissions requested, the number of total permissions and the risk weight calculated through the combination of permissions in an application. Our implementation results for 3197 benign apps collected from Google Play and 372 malware apps from different sources show that Sandroid achieves 98% detection accuracy, greater than any existing methods.-
dc.description.tableofcontents1. Introduction 6 1.1 Background 6 1.2 Android Architecture 8 1.3 Android Security Model 10 1.4 Android Applications 10 1.5 Android Malwares and Security Issues 11 2. Related Work 13 3. Description of the Datasets 16 3.1 Benign Apps 16 3.2 Malware Dataset 16 3.3 Permissions 17 4. Machine Learning Algorithm 20 4.1 Support Vector Machines (SVM) 20 4.2 SVM Classification 20 5. Proposed System 22 5.1 System Architecture 22 5.2 Extracted Features 23 5.3 Implementation 26 5.3.1 Tools Employed and Environment 26 5.3.2 Classification 26 5.3.3 Android Implementation 27 5.3.4 Web Based Implementation 27 6. Experimental Results 29 7. Conclusion 32 8. Reference 33-
dc.language.isoeng-
dc.publisherThe Graduate School, Ajou University-
dc.rights아주대학교 논문은 저작권에 의해 보호받습니다.-
dc.titleAndroid Malware Detection and Classification through Permission Based Analysis using SVM-
dc.typeThesis-
dc.contributor.affiliation아주대학교 일반대학원-
dc.contributor.department일반대학원 컴퓨터공학과-
dc.date.awarded2013. 8-
dc.description.degreeMaster-
dc.identifier.localId571062-
dc.identifier.urlhttp://dcoll.ajou.ac.kr:9080/dcollection/jsp/common/DcLoOrgPer.jsp?sItemId=000000015053-
dc.subject.keywordAndroid-
dc.subject.keywordMalware-
dc.subject.keywordDetection-
Appears in Collections:
Graduate School of Ajou University > Department of Computer Engineering > 3. Theses(Master)
Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse