Model for Phishing Websites Classification Using Artificial Neural Network

Abstract

Internet users might be exposed to various forms of threats that can create economic harm, identity fraud, and lack of faith in e-commerce and online banking by consumers as the internet has become a necessary part of everyday activities. Phishing can be regarded as a type of web extortions described as the skill of imitating an honest company's website aimed at obtaining private information for example usernames, passwords, and bank information. The accuracy of classification is very significant in order to produce high accuracy results and least error rate in classification of phishing websites. The objective of this research is to model a suitable neural network classifier and then use the model to class the phishing website data set and evaluate the performance of the classifier. This research will use a phishing website data set which was retrieved from UCI repository and will be experimented using Encog Workbench tool. The main expected outcome from this study is the preliminary ANN classifier which classifies the target class of the phishing websites data set accurately, either phishy, suspicious or legitimate ones. The results indicate that ANN (9-5-1) model outperforms other models by achieving the highest accuracy and the least MSE value which is 0.04745.