基于结构化文档的钓鱼网站检测算法  

Phishing detection algorithm based on structured document

作　　者：刘博文 王雨琪 林果园[1,2] LIU Bo-wen;WANG Yu-qi;LIN Guo-yuan(School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116,China;Mine Digitization Engineering Research Center of Ministry of Education,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]中国矿业大学计算机科学与技术学院,江苏徐州221116 [2]中国矿业大学矿山数字化教育部工程研究中心,江苏徐州221116

出　　处：《计算机工程与设计》2019年第10期2791-2798,共8页Computer Engineering and Design

基　　金：江苏省产学研前瞻性联合研究基金项目(BY201602604)

摘　　要：为利用网站设计的视觉原则并降低钓鱼者修改网页代码组织方式对钓鱼检测的影响,提出基于网页主视觉区域的结构化文档DMVA (document based on main visual area)检测钓鱼网站。提出子间归并算法生成网页的视觉分块;基于用户的视觉行为,结合层DOM树的分层结构,提出主视觉区域的思想,获取网页的分层主视觉区域中文本信息,构造DMVA;提出相关网站集,计算待测网站和相关网站集中网页间的DMVA的相似性,检测钓鱼网站。实验结果表明,基于DMVA检测钓鱼网站算法钓鱼检测方法具有较好的准确度。To use visual principles of website design and to reduce the impacts of phishers’ modification of webpage code organization on phishing,document based on the main visual area of the webpage,DMVA,was proposed to be applied on phishing detection.The sub-merging algorithm was proposed to generate the visual segmentation of the webpage.Based on the user’s visual behavior and the hierarchical structure of the layer DOM tree,the idea of the main visual area was used to obtain the text information in the hierarchical main visual area of the webpage,and the DMVA was constructed.The relevant website collection was proposed and the similarity of the DMVA between the website under test and the relevant website centralized web page was calculated to detect the phishing website.Experimental results show that the phishing detection method proposed has better accuracy.

关 键 词：钓鱼检测 结构化文档 视觉分块 视觉行为 分层结构 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]