DETECTION OF PHISHED WEBSITES

Abstract: Phishing, a criminal act of gathering personal, bank and credit card information by sending out forged e- mails with fake websites, has become the most popular recitation among the criminals of the Web. Phishing attacks are becoming more and more sophisticated and are constantly on the rise. Phishing is a major threat to information security and personal privacy. The total number of URLs used to host phishing attacks are increased to 1, 75,229 in the second quarter of 2013, up from 1, 64,023 in the first quarter of 2013 according to APWG, a Phishing Activity Trends Report. Many anti-phishing solutions, such as content analysis and HTML code analysis, rely on this property to detect fake web pages. However, these techniques failed, as phishers are now composing phishing pages with non-analyzable elements, such as images and flash objects. This paper proposes a new phishing detection scheme based on URL domain similarity, IP matching and image matching. This paper correctly estimates the phished website in three phases. At first it estimates similarity with authorized URL database, here itself we eliminate, in second phase we confirm based on IP matching and in final phase we find number of key-points matched.

Keywords: Phishing; anti-phishin;,URL similarit;,ip matching; image matching.