Enhanced detection of Phishing through pattern based recognition for securing human interaction through WEB pages (original) (raw)

Phasing the WEB sites is the most dangerous threat posed in proper functioning of the WEB sites especially those that are concerned with e-commerce sites and those sites that deal confidential information of the users such as details related to banking. Many attackers mimic the web pages of the application that collect confedentional information of the users. It has been a challenge to recognize the web pages instated by the attackers and then take corrective actions so that the users are exploited. Many have attempted to detect the Phasing pages based on visual similarity and the attackers mimic the WEB pages such that it quite complicated to detect the Phishing pages. In this paper a method and an approach presented that is centered on conditional information collected through the WEB pages without much bothering about the Visual presentation of the content or the layout. A repository of the word phrases which are type identified are maintained that are related to confidential information. The confidential data related to a set of Phished pages obtained from Phishedpages.com are generated and stored in a database. Every time A web page is to be processed, confidential data refereed in the WEB page is extracted in consideration with the database of repository of confidential data phrases and the similarly of the same is detected based on Euclidian distance. The process of detection is done on the WEB server side with the client hinted with the possibility of Phishing.