钓鱼网页特征向量提取方法研究  

The Research of Extracting the Phishing Web Features Vector

作　　者：司响[1] 李秋锐[1] 宋士超[1] 

机构地区：[1]中国人民公安大学,北京100038

出　　处：《信息网络安全》2011年第9期201-203,共3页Netinfo Security

摘　　要：随着电子商务和在线交易的增加,网络钓鱼已经成为最严重的一种网络犯罪形式。文章从网页中包含的超链接这一角度出发,给出了网页的身份特征,并结合网页ICP号,版权所有者以及网页行为等对网页特征进行了提取,得到了钓鱼网页的特征向量,为及时准确检测钓鱼网页提供了依据。As the Electronic Commerce and On-line Trade expand, phishing has already become one of the severest forms of network crimes. In this paper, the identity features of web-pages are given based on the hyperlinks included in the web-pages, and then web-page features are extracted employing ICP of web-pages, owner of the copyright, web-page behaviors and so on, With the extraction of feature vectors of phishing web-pages, more evidences acquired render the detection ofphishing web-pages with more accuracy and shorter time-consumption.

关 键 词：钓鱼网页 网页特征 特征向量 

分 类 号：TP393.092[自动化与计算机技术—计算机应用技术]