A Framework for Detecting Phishing Websites using GA based Feature Selection and ARTMAP based Website Classification
Priya Saravanan, S. Subramanian
Abstract
Nowadays, Phishing attack has gained more attention among all the other attacks existing in online social media. The fraudulent E-mail sent form the fake website that looks like the legitimate website is the initial carter for launching the phishing attacks. This is a kind of social engineering attack in which, the user is targeted for stealing the personal information, viz., user name, password, and banking credentials for committing the financial crimes. The existing phishing website detection methods suffer from two issues in terms of feature selection scheme that does not consider the right set of features for detection and the classifier which is trained with the poor hyper parameters. In this paper, the phishing websites are detected by extracting the various features from the collection of phishing and legitimate websites obtained from PhishTank and starting point directory service. This constructed feature vector is further processed by the proposed feature selection module GenFea to obtain the reduced set of features. This reduced feature vector is further processed by the proposed phishing detection module PhiDec to predict the type of a website. The performance of the proposed approach is compared with the existing machine learning classifiers and neural network classifiers. From the experimental results, it is observed that the proposed approach outperformed the other existing classifiers for detecting the phishing websites.