A Survey and Taxonomy of Anti-Phishing Techniques for Detecting Fake Websites

Abstract

Phishing is a threat it causes damage to the Organization, Users, Employees, etc., by stealing sensitive information like Username, Password, Credit card numbers, CVVs, and other details. Fake Websites are widely used to steal data by sending URL to a large number of users through emails SMS, and Popups. Fake websites also called phishing websites which are very similar the Trusted and Famous websites. Phishing websites have a very less life span but every year Phishing sites are gradually increasing. In 2016, loss of 4.2 billion to the organization and a 1.25 lakh crores financial loss in India in 2019. Anti-Phishing Working Group detected the phishing websites by collecting, and analyzing the Emails containing URLs and reported. We cannot identify by seeing the User interface of websites. Many methods are existed to identify Phishing websites. Widely used methods are Blacklist or Whitelist approach, Content-based approach, URLs based, Visual Similarity, Machine Learning models, etc., every method requires different inputs. Inputs are URLs, Source Codes, Website text data, Website URLs statistical data, Images on websites. This survey mainly focuses on the various methodologies, Technologies, and Accuracy of the approaches.