多策略网页恶意代码检测算法的实现  

Detection of Malicious Web Code Based on Multiplepolicies

作　　者：张小萍[1] 黄海明 ZHANG Xiaoping;HUANG Haiming(College of Computer and Electronic Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《太原师范学院学报（自然科学版）》2021年第1期73-76,共4页Journal of Taiyuan Normal University:Natural Science Edition

摘　　要：随着互联网的迅速发展,人们在浏览网页的时候容易受到网页恶意代码的攻击.针对这些问题,提出了一种基于多策略的网页恶意代码检测方法.对恶意网页代码特征进行分析,通过运用词频统计的方法对网页代码进行特征挖掘,获取关键特征值后,分别利用支持向量机算法、朴素贝叶斯算法、神经网络算法和多策略的算法建立分类模型,设计实验对4种分类模型进行性能测试.实验表明,提出的基于多策略的网页恶意代码检测方法比单一的检测方法准确率和精准率要高,召回率较低.With the rapid development of the Internet,people are vulnerable to malicious code when browsing the web.To solve these problems,a multi-strategy-based malicious code detection method for web pages is proposed.The feature of malicious web code is analyzed,and the feature mining of web code is carried out by using word frequency statistics method.After obtaining the key eigenvalues,the classification model is established by using support vector machine algorithm,naive Bayes algorithm,neural network algorithm and multi-strategy algorithm respectively.The performance of the four classification models is tested by design experiments.Experiments show that the proposed multi-strategy-based malicious code detection method is more accurate and less recall than a single detection method.

关 键 词：多策略 网页恶意代码 朴素贝叶斯 支持向量机 神经网络 

分 类 号：TP309.5[自动化与计算机技术—计算机系统结构]