Abstract
Corporations that offer online trading can achieve a competitive edge by serving worldwide clients. Nevertheless, online trading faces many obstacles such as the unsecured money orders. Phishing is considered a form of internet crime that is defined as the art of mimicking a website of an honest enterprise aiming to acquire confidential information such as usernames, passwords and social security number. There are some characteristics that distinguish phishing websites from legitimate ones such as long URL, IP address in URL, adding prefix and suffix to domain and request lJRL, etc. In this paper, we explore important features that are automatically extracted from websites using a new tool instead of relying on an experienced human in the extraction process and then judge on the features importance in deciding website legitimacy. Our research aims to develop a group of features that have been shown to be sound and effective in predicting phishing websites and to extract those features according to new scientific precise rules.