Ammar Odeh, Ismail Keshta, Ibrahim Abu Alhaol, Ahmad Abushakra
Phishing is a Social Engineering attack technique that is commonly used to obtain user-sensitive information such as login credentials, credit and debit card information, and so on. A phishing website has the same name and appearance as an official website. Also known as a fake website, which is designed to trick a person into stealing their identity. In this paper, we introduce a novel technique for detecting phishing websites on the client-side using a machine learning technique. We use the extraction framework rule in this system paper to extract the features of a website using only the URL. The proposed algorithm uses a dataset contains 30 different URL characteristics that will be used by this same Multilayer Perceptron Classification machine learning model to determine the website's truthfulness. The model is trained using a dataset containing 11,055 tuples. These processes take place on the client-side. The proposed system introduces a high performance on the 70:30 split ratio.