Feature Selection for Phishing Website Classification

Abstract

Phishing is an attempt to obtain confidential information about a user or an organization. It is an act of impersonating a credible webpage to lure users to expose sensitive data, such as username, password and credit card information. It has cost the online community and various stakeholders hundreds of millions of dollars. There is a need to detect and predict phishing, and the machine learning classification approach is a promising approach to do so. However, it may take several phases to identify and tune the effective features from the dataset before the selected classifier can be trained to identify phishing sites correctly. This paper presents the performance of two feature selection techniques known as the Feature Selection by Omitting Redundant Features (FSOR) and Feature Selection by Filtering Method (FSFM) to the 'Phishing Websites' dataset from the University of California Irvine and evaluates the performance of phishing webpage detection via three different machine learning techniques: Random Forest (RF) tree, Multilayer Perceptron (MLP) and Naive Bayes (NB). The most effective classification performance of these machine learning algorithms is further rectified based on a selected subset of features set by various feature selection methods. The observational results have shown that the optimized Random Forest (RFPT) classifier with feature selection by the FSFM achieves the highest performance among all the techniques.