一种欺骗网页检测判定算法

欺骗网页与正常网页有着极其相似的特征,诱导并欺骗用户输入个人机密信息,严重威胁着电子商务正常运行.基于此,提出了一个欺骗网页检测算法.算法首先对网页进行分割,然后提取各个块的特征及其相对位置关系,得到网页特征关系图,并以此计算出两个网页之间的相似度.如果发现可疑网页与某个受保护网页之间的相似度小于预设值,判定该可疑网页为针对受保护网页的欺骗网页.实验结果表明,本算法可以有效检测欺骗网页,具有一定的实用性.

Decision Algorithm for Detecting Deceptive Web Page

Deceptive web pages have similarity with normal web pages and induce and cheat users to enter personal secret information,which poses a severe threat to the normal development of e-commerce.In light of this situation,an algorithm for detecting deceptive web pages was proposed,which was used to segment the web pages first.Then every block's characteristics and its relative position relationship were extracted to form characteristic relation diagram of web pages,by which amount of similarity between two pages...