Affiliations: Department of Computer Engineering, Chosun University,
Gwangju, Korea
Note: [] Corresponding author: Department of Computer Engineering, Chosun
University, Gwangju, Korea. Pan-Koo Kim, Tel.: +82 62 230 7636; Fax: +82 62 230
7636; E-mail: pkkim@chosun.ac.kr
Abstract: Large parts of attacks targeting the web are aiming at the weak
point of web application. Even though SQL injection, which is the form of XSS
(Cross Site Scripting) attacks, is not a threat to the system to operate the
web site, it is very critical to the places that deal with the important
information because sensitive information can be obtained and falsified. In
this paper, the method to detect themalicious SQL injection script code which
is the typical XSS attack using n-Gram indexing and SVM (Support Vector
Machine) is proposed. In order to test the proposed method, the test was
conducted after classifying each data set as normal code and malicious code,
and the malicious script code was detected by applying index term generated by
n-Gram and data set generated by code dictionary to SVM classifier. As a
result, when the malicious script code detection was conducted using n-Gram
index term and SVM, the superior performance could be identified in detecting
malicious script and the more improved results than existing methods could be
seen in the malicious script code detection recall.
