Phishing Websites Detection using Machine Learning with URL Analysis
Areti Nagendra Soma Charan, Y.F. Chen, Jiann-Liang Chen
Abstract
Phishing has become a vital concern for security researchers due to the anonymous structure of the Internet. Phishing attacks are becoming more prevalent, and due to rapid technological advancements, hackers are developing increasingly sophisticated phishing kits. Therefore, more attention to be paid to preventing phishing scams. This study uses URLs as a dataset to detect phishing websites. The dataset contains 6000 URLs, from which ten features were extracted and utilized to determine if the website was phishing or not. Eight machine learning algorithms were designed for this research. The performance analysis results show that the Multilayer perceptron algorithm got the highest accuracy of 85.41% and an F1 score of 85.17% compared with other algorithms.