Testing Phishing Detection Criteria and Methods

Abstract

Phishing attacks have increased in the last years despite the use of anti-phishing filters. This is mainly caused by the diversity of phishers trials and the improvement on targeting potential victims on internet. Usually phishers employ social engineering techniques trying to convince users to supply confidential data using the email as the dissemination vehicle. Phishers disguise attacks as trustworthy organizations by cloning websites. According to international monitoring, phishing causes real injury mainly to banks and government institutions. This paper proposes important features to detect phishing attacks employing data mining techniques to evaluate and compare them. In this work we have used public corpora of phishing messages. As a main result we have identified main phishing detection criteria, which have been evaluated and best accurate results were achieved using neural nets and decision trees.