부산대학교 도서관

In recent years, advancements in Internet and technologies have led to a major increase in electronic trading during which consumers make online purchases and transactions. This growth results in unauthorized access to users’ sensitive information and damages the resources of an enterprise. In terms of Website interface and uniform resource locator (URL), most phishing Webpages look the image of the particular Webpages. because of inefficient security technologies, there’s an exponential increase within the number of victims. The anonymous and uncontrollable framework of the Web is more at risk of phishing attacks. Existing research works show that the performance of the phishing detection system is restricted. There’s a requirement for an intelligent technique to shield users from cyber-attacks. During this study, a model has been proposed that a URL detection technique that supports machine learning approaches. In this work, phishing websites has been detected using autoML and convolution neural network (CNN) techniques with and accuracy of 98% and 85% respectively.