Feature Selection for Phishing Website by Using Naive Bayes Classifier

The Internet is gradually becoming a necessary and important tool of human’s everyday life. But internet users might have poor security for different kinds of web threats, which may have an effect on monetary damage and loss of clients’ trust in online trading and online banking. Phishing is described as a skill of impersonating a website and trustful project aiming to get private and secret information such as a user name and password and social security and credit card number. However, there is no single solution that can catch most phishing attacks. This paper discusses the Feature Selection for Phishing website by using the Naive Bayes classifier. The dataset used in this study has thirty-one attributes. The aim of this paper is to reduce the dataset and find the best performance system having the ability to make right classifications for phishing datasets. We used feature selection algorithms for reducing the dataset and system performance, also comparing among feature selection algorithms’ performance for each dataset, then making a classification for the dataset by the naïve classifier.