IntAnti-Phish

Abstract

Among the cybercriminals, the popularity of phishing has been rapidly growing day by day. Therefore, phishing has become an alarming issue to solve in the field of cyber security. Many researchers have already proposed several anti-phishing approaches to detect phishing in terms of email, webpages, images, or links. This study also aimed to propose and implement an intelligent framework to detect phishing URLs (Uniform Resource Locator). It has been observed in this study that Back propagation Neural Network-based systems need to tune various hyper parameters to obtain the optimized output. With a maximum of two hidden layers along with 400 epochs can reach maximum accuracy of 0.93, the minimum mean squared error of 0.27, and also a minimum error rate of 0.07 which measurements lead this study to generate an optimized model for phishing detection. The detailed process of feature extraction and optimized model generation along with the detection of unknown URLs are considered and proposed during the development of IntAnti-Phish (An Intelligent Anti-Phishing Framework).