Classifying Malicious Web Pages by Using an Adaptive Support Vector Machine
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In order to classify a web page as being benign or malicious, we designed 14basic and 16 extended features. The basic features that we implemented were selected to represent the essential characteristics of a web page. The system heuristically combines two basic features into one extended feature in order to effectively distinguish benign and malicious pages. The support vector machine can be trained to successfully classify pages by using these features. Because more and more malicious web pages are appearing, and they change so rapidly, classifiers that are trained by old data may misclassify some new pages. To overcome this problem, we selected an adaptive support vector machine (aSVM) as a classifier. The aSVM can learn training data and can quickly learn additional training data based on the support vectors it obtained during its previous learning session. Experimental results verified that the aSVM can classify malicious web pages adaptively.
Abstract
In order to classify a web page as being benign or malicious, we designed 14basic and 16 extended features. The basic features that we implemented were selected to represent the essential characteristics of a web page. The system heuristically combines two basic features into one extended feature in order to effectively distinguish benign and malicious pages. The support vector machine can be trained to successfully classify pages by using these features. Because more and more malicious web pages are appearing, and they change so rapidly, classifiers that are trained by old data may misclassify some new pages. To overcome this problem, we selected an adaptive support vector machine (aSVM) as a classifier. The aSVM can learn training data and can quickly learn additional training data based on the support vectors it obtained during its previous learning session. Experimental results verified that the aSVM can classify malicious web pages adaptively.
참고문헌 (12)
- Peter Likarish, "Obfuscated Malicious JavaScript Detection using Classification Techniques", Proceedings of the 4th International Conference on Malicious and Unwanted Software, pp.47~54 (2009)
- "LIBSVM: A Library for Support Vector Machines" (2001)[URL]
- Jun Yang, "Cross-Domain Video Concept Detection using Adaptive SVMs", ACM Multimedia, pp.188~197 (2007)
- Y. Choi, "Automatic Detection for JavaScript Obfuscation Attacks in Web Pages through String Pattern Analysis", International Journal of Security and Its Applications, 4(2), pp.13~26 (2010)
- B. Feinstein, "Caffeine Monkey: Automated Collection, Detection and Analysis of Malicious JavaScript" (2007), Black Hat
- B. Kim, "Suspicious Malicious Web Site Detection with Strength Analysis of a JavaScript Obfuscation", International Journal of Advanced Science and Technology, 26 (2011)
- Christian Seifert, "Identification of Malicious Web Pages with Static Heuristics", Telecommunication Networks and Applications Conference, pp.91~96 (2008)
- Y.-T. Hou, "Malicious Web Content Detection by Machine Learning", Expert Systems with Applications, 378, pp.55~60 (2010)
- J. Lee, "Malicious Web Page Detection using Malicious Code Spreading Pattern", The 3rd International Conference on Internet, pp.195~200 (2011)
- Simon Haykin, "Neural Networks and Learning Machines, In Chapter 6" (2008), Prentice Hall
- Jun Yang, "A Framework for Classifier Adaptation and its Applications in Concept Detection", ACM Int’l Conf. on Multimedia Information Retrieval (2008)
- B. Kim, "Suspicious Malicious Web Site Detection with Strength Analysis of a JavaScript Obfuscation", International Journal of Advanced Science and Technology, 26, pp.19~32 (2011)