A Study on security enhancement of android application and routing protocol = 안드로이드 어플리케이션 및 라우팅 프로토콜 보안성 강화에 관한 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 436
  • Download : 0
As mobile technology has developed, smartphone technology has also grown rapidly. Among various smartphones, the android-based phone is the most used smartphone in the world. However, malicious behav-iors targeting android phones have rapidly increased in recent years. One of these malicious behaviors is dis-tribution of applications including malicious codes. Another malicious behavior is routing disruption attacks on the Mobile Ad hoc Network (MANET). In this thesis, we have studied security enhancement of the an-droid application and routing protocol with the goal of reducing the impacts from these behaviors. This study mainly focuses on detecting malicious android application based on machine learning methods. First, an efficient static analysis method is proposed for detection of malicious android applica-tions. Because of the absence of any application inspection system, anyone can freely upload applications developed for the android market, and the number of android applications is increasing rapidly. Unfortu-nately, this open accessibility draws the attention of malicious application developers as well, and there are already many malicious applications. To detect malicious applications, previous approaches have used dynamic and static analysis. Dynamic analysis has a high detection rate, but uses lots of resources and takes a long time. On the other hand, detection using static analysis is quick, and uses a relatively small amount of resources. Thus, a large number of applications on android market could be analyzed by the static analysis. To improve the detection rate of static methods, several researchers have included machine learning in their analyses, with unsatisfactory results. In this study, we propose to use Application Programming Interface (API) functions as features in machine learning to reduce the false negative rate and false positive rate; and to enable a cost sensitive method for minimizing the false negative rate. This is important, b...
Advisors
Kim, Se-Hunresearcher김세헌
Description
한국과학기술원 : 산업및시스템공학과,
Publisher
한국과학기술원
Issue Date
2014
Identifier
568503/325007  / 020107114
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 산업및시스템공학과, 2014.2, [ vii, 82 p. ]

Keywords

Machine Learning; 웜홀 공격; 이상 탐지; 정적 분석; 악성 안드로이드 어플리케이션; 머신러닝; Malicious Android Application; Static Analysis; Anomaly Detection; Wormhole Attack

URI
http://hdl.handle.net/10203/196985
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=568503&flag=dissertation
Appears in Collection
IE-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0