Comparison of HMM and SVM schemes in detecting mobile Botnet

최병하; Kyungsan CHO

As mobile devices have become widely used and developed, PC based malwares can be movingtowards mobile-based units. In particular, mobile Botnet reuses powerful malicious behavior ofPC-based Botnet or add new malicious techniques. Different from existing PC-based Botnetdetection schemes, mobile Botnet detection schemes are generally host-based. It is because mobileBotnet has various attack vectors and it is difficult to inspect all the attack vector at the sametime. In this paper, to overcome limitations of host-based scheme, we compare two network-basedschemes which detect mobile Botnet by applying HMM and SVM techniques. Through theverification analysis under real Botnet attacks, we present detection rates and detection properties of two schemes.

Citation status

KCI Citation Counts (1)
열림/닫힘 버튼
REFERENCES (18)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[journal] 최병하 / 2009 / An Improved Detecting Scheme of Malicious Codes using HTTP Outbound Traffic / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 14(9) : 47~54

[confproc] ByungHa Choi / 2013 / Detection of Mobile Botnet Using VPN / Procs. of The Seventh International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS-2013) : 142~148

[confproc] G. Delac / 2011 / Emerging security threats for mobile platforms / Procs. of the 34th International Convention, MIPRO 2011 : 1468~1473

[confproc] AK. Tyagi / 2011 / A Wide Scale Survey on Botnet / Procs. of International Journal of Computer Applications 34(9) : 10~23

[journal] Byungha Choi / 2013 / Two-Step Hierarchical Scheme for Detecting Detoured Attacks to the Web Server / ComSIS 10(2) : 633~649

[confproc] Gu, Guofei / 2008 / BotMiner: Clustering analysis of network traffic for protocol-andstructureindependent botnet detection / Procs. of the 17th conference on Security symposium

[report] NQ Mobile / 2012 / NQ Mobile 2011 Mobile Security Report

[confproc] Iker Burguera / 2011 / Crowdroid: behavior-based malware detection system for android / Procs. of the 1st ACM workshop on Security and privacy in smartphones and mobile devices / ACM : 15~26

[confproc] L. Xie / 2010 / pBMDS:a behavior-based malware detection system for cellphone devices / Procs. of the third ACM conference on Wireless network security / ACM : 37~48

[confproc] A. Bose / 2008 / Behavioral detection of malware on mobile handsets / Procs. of the 6th international conference on Mobile systems, applications, and services / ACM : 225~238

[confproc] Portokalidis, Georgios / 2010 / Paranoid Android:versatile protection for smartphones / Procs. of the 26th Annual Computer Security Applications Conference / ACM

[journal] Falletta, Vincenzo / 2009 / Detecting scanners: empirical assessment on a 3G network / International Journal of Network Security 9(2) : 143~155

[journal] Vural, Ickin / 2012 / Combating Mobile Spam through Botnet Detection using Artificial Immune Systems / Journal of Universal Computer Science 18(6) : 750~774

[journal] Edson J. R. Justino / 2005 / A comparison of SVM and HMM classifiers in the off-line signature verification / Pattern Recognition Letters 26(9) : 1377~1385

[confproc] Yi-Lin Lin / 2005 / Speech emotion recognition based on HMM and SVM / Machine Learning and Cybernetics, 2005. Procs of 2005 International Conference on 8 : 18~21

[journal] Hong-Zhong Huang / 2007 / A Comparison Study of Support Vector Machines and Hidden Markov Models in Machinery Condition Monitoring / Journal of Mechanical Science and Technology / 대한기계학회 21(4) : 607~615

[web] / Wireshark / http://wireshark.com/

[journal] B-H. Juang / 1990 / The segmental K-means algorithm for estimating parameters of hidden Markov models / Procs. of Acoustics, Speech and Signal Processing, IEEE Transactions on 38(9) : 1639~1641

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status