Intelligent phishing website detection using random forest classifier

Phishing is defined as mimicking a creditable company's website aiming to take private information of a user. In order to eliminate phishing, different solutions proposed. However, only one single magic bullet cannot eliminate this threat completely. Data mining is a promising technique used to detect phishing attacks. In this paper, an intelligent system to detect phishing attacks is presented. We used different data mining techniques to decide categories of websites: legitimate or phishing. Different classifiers were used in order to construct accurate intelligent system for phishing website detection. Classification accuracy, area under receiver operating characteristic (ROC) curves (AUC) and F-measure is used to evaluate the performance of the data mining techniques. Results showed that Random Forest has outperformed best among the classification methods by achieving the highest accuracy 97.36%. Random forest runtimes are quite fast, and it can deal with different websites for phishing detection.