A Static Malicious Javascript Detection Using SVM

DOI

10.2991/iccsee.2013.56How to use a DOI?

Keywords

SVM, static detection, malicious script detection

Abstract

Malicious script,such as JavaScript, is one of the primary threats of the network security. JavaScript is not only a browser scripting language that allows developers to create sophisticated client-side interfaces for web applications, but also used to carry out attacks taht used to steal users' credentials and lure users into providing sensitive information to unauthorized parties. We propose a static malicious JavaScript detection techniques based on SVM(Support Vector Machine). Our approach combines static detection with machine learning technique, to analyze and extract malicious script features,and use the machine learning technology,SVM, to classify the scripts.This technique has the characteristics of high detection rate,low false positive rate and the detection of unknown attacks. Applied to experiments on the prepared data set, we achieved excellent detection performance.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wei-Hong WANG
AU  - Yin-Jun LV
AU  - Hui-Bing CHEN
AU  - Zhao-Lin FANG
PY  - 2013/03
DA  - 2013/03
TI  - A Static Malicious Javascript Detection Using SVM
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 214
EP  - 217
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.56
DO  - 10.2991/iccsee.2013.56
ID  - WANG2013/03
ER  -