Speeding up Anti-Phishing Tools Development using Self-Structuring Neural Network

Internet has become an essential component of our everyday social and financial activities. However, internetusers may be vulnerable to different types of web-threats. Phishing is considered as a form of web-threats that is defined as the art of impersonating a website of an honest enterprise aiming to obtain confidential information such as usernames, passwords and social security number. To date, there is no single solution that can capture every phishing attack. In this article, we proposed an intelligent model for predicting phishing attacks based on Artificial Neural Network “ANN” particularly, selfstructuring neural networks. Phishing is a continuous problem where features significant in determining the type of webpages are constantly changing. Thus, we need to regularly retrain the anti-phishing tool to cope with these changes. Our model speeds up the anti-phishing tool development by automating the process of structuring an ANN model. Our model shows high acceptance for noisy data, fault tolerance and high prediction accuracy. Several experiments were conducted in our research, the number of epochs differ in each experiment. From the results, we find that all produced structures have high generalization ability. KeywordsWeb Threat, Phishing, Anti-Phishing, Neural Network, Data Mining.