A Machine Learning Model for Predicting Phishing Websites

Abstract There are various types of cybercrime, and hackers often target specific ones for different reasons, such as financial gain, recognition, or even revenge. Cybercrimes can occur anywhere in the world, as the location of both the victim and the criminal is not a limiting factor. Different countries may have different common types of cybercrime, influenced by factors such as the country's economic situation, level of internet activity, and overall development. Phishing is a prevalent type of cybercrime in the financial sector, regardless of the country's circumstances. While the phishing techniques used in developed countries may differ from those in developing countries, the impact remains the same, resulting in financial losses. In our work, a dataset consisting of 48 features extracted from 5,000 phishing webpages and 5,000 legitimate webpages was used to predict whether a website is phishing or not, achieving an accuracy of 98%.