New Filtering Approaches for Phishing Email

ABSTRACT: The aim of making web users believe that they are communicating with a trusted entity for the purpose of stealing account information, logon credentials, and identity information in general. This attack method, commonly known as "phishing," is most commonly initiated by sending out emails with links to spoofed websites that harvest information. Phishing is a significant problem involving fraudulent email and web sites that trick unsuspecting users into revealing private information. Phishing has become more and more complicated and sophisticated attack can bypass the filter set by antiphishing techniques. Most phishing emails aim at withdrawing money from financial institutions or getting access to private information and is a serious threat to global security and economy. Phishing filters are necessary and widely used to increase communication security. In this paper we describe a number of features that are particularly well-suited to identify phishing emails. These include statistical models for the low-dimensional descriptions of email topics, sequential analysis of email text and external links, the detection of embedded logos as well as indicators for hidden salting