A Novel Machine Learning Approach to Detect Phishing Websites

Phishing can be described as a way by which someone may try to steal some personal and important information like login id's, passwords, and details of credit/debit cards, for wrong reasons, by appearing as a trusted body. Many websites, which look perfectly legitimate to us, can be phishing and could well be the reason for various online frauds. These phishing websites may try to obtain our important information through many ways, for example: phone calls, messages, and pop up windows. So, the need of the hour is to secure information that is sent online and one concrete way of doing so is by countering these phishing attacks. This paper is focused on various Machine Learning algorithms aimed at predicting whether a website is phishing or legitimate. Machine learning solutions are able to detect zero hour phishing attacks and they are better at handling new types of phishing attacks, so they are preferred. In our implementation, we managed an accuracy of 98.4% in prediction a website to be phishing or legitimate.