Feature extraction process: A phishing detection approach

In order to circumvent the adverse effect of fraudulent acts committed on the internet by adversaries, different researchers have proposed various solution to this problem. One of this online fraudulent act is website phishing. Website phishing is the act of luring unsuspecting online users into divulging private and confidential information which can be used by the phisher in fraud, blackmail or other ways to negatively affect the users involved. In this paper, we propose noble features to better improve the accuracy of machine learning algorithms in classifying phish. Furthermore, ranking of these new features according to their weighted values with existing features is carried out in order to show the potency of the new feature as compared with the current features. The experimental result of the research shows that the new features are highly potent and can be used to enhance the better performance of machine learning algorithm used for phishing detection.

I. Introduction

Social engineering attacks targeting users not computers or systems and it is designed to elicit sensitive or confidential information from users. Most social engineering attacks are classified as phishing attacks. And there are different techniques for phishing in order to deceive the users such as phishing by email, instant messages, SMS and website. These techniques help the phisher to lure unsuspecting online users into divulging personal information such as bank account information, website login information, and other sensitive information that can be used by a third party for illegal profit, blackmailing etc.