计算机工程与应用2019，Vol.55Issue(18)：89-94,6.DOI:10.3778/j.issn.1002-8331.1808-0005
基于卷积神经网络的JavaScript恶意代码检测方法
Detection Approach of Malicious JavaScript Code Based on Convolutional Neural Network
摘要
Abstract
Time and manpower have been wasted largely in the process of features extraction when JavaScript malicious code detection methods of machine learning are used, and these frequently-used methods have failed to meet the actual needs in the current information explosion. A JavaScript malicious code detecting method based on convolution neural net-work have been proposed in this paper. The sample data are collected through the crawler tool to obtain the benign and mali-cious JavaScript script code. The JavaScript samples are converted into the corresponding gray scale images, simultane-ously, the image dataset is established. The image data set is trained when the convolution neural network model is con-structed, so the model has obtained the ability to detect JavaScript malicious code. The experimental results show that the accuracy of the method is 98.9% for the 5, 800 JavaScript labeled images collected.关键词
卷积神经网络/JavaScript脚本/灰阶图像/机器学习/Web安全Key words
Convolutional Neural Network(CNN)/JavaScript’s scripts/grayscale image/machine learning/Web security分类
信息技术与安全科学引用本文复制引用
龙廷艳,万良,邓烜堃..基于卷积神经网络的JavaScript恶意代码检测方法[J].计算机工程与应用,2019,55(18):89-94,6.基金项目
贵州省科学基金(黔科合J字[2011(] 2328),黔科合LH字[2014(] 7634)). （黔科合J字[2011(] 2328）
