基于AdaCostBoost算法的网络钓鱼检测  

Phishing Detection System Based on AdaCostBoost Algorithm

作　　者：曾传璜[1] 李思强[1] 张小红[1] 

机构地区：[1]江西理工大学信息工程学院,赣州341000

出　　处：《计算机系统应用》2015年第9期129-133,共5页Computer Systems & Applications

基　　金：国家自然科学基金(11062002)

摘　　要：针对日益严重的网络钓鱼攻击,提出机器学习的方法进行钓鱼网站的检测和判断.首先,根据URL提取敏感特征,然后,采用AdaBoost算法进行训练出分类器,再用训练好的分类器对未知URL检测识别.最后,针对非平衡代价问题,采用了改进后的AdaBoost算法--AdaCostBoost,加入代价因子的计算.实验结果表明,文中提出的网络钓鱼检测方法,具有较优的检测性能.For increasing serious phishing attacks, machine-learning method is proposed to detect phishing webs. Firstly, sensitive features are extracted from the URL, then, using Ada Boost algorithm to get the trained classifier, and then the classifier is used to detect unknown URLs. Finally, considering of non-equilibrium problems of AdaBoost, the paper puts forward the improved learning algorithm called AdaCostBoost, which contains computation of cost factors. According to the experiment result, the proposed phishing detection method has better detection performance.

关 键 词：网络钓鱼 敏感特征 AdaCostBoost 分类器 代价因子 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]