Phishing Website Detection: A Dataset-Centric Approach for Enhanced Security
Sultan Ahmad, Md. Alimul Haque, Hikmat A. M. Abdeljaber, Mohammad Ubaidullah Bokhari, Jabeen Nazeer, B. K. Mishra · Data & Metadata · 2024
Introduction; Phishing involves cybercriminals creating fake websites that appear to be real sites with the aim of obtaining personal information. With the increasing sophistication of phishing websites, machine learning today provides a useful approach to scan and counter such attacks. Objective; In this study, we seek to apply machine learning algorithms on the dataset - Phishing_Legitimate_full.csv – which consists of phishing websites and genuine websites that have been labeled. Method; This paper aims to identify the most effective feature selection method for predicting phishing websites. Result; The findings highlight the potential of machine learning in enhancing cybersecurity by automating threat detection and intelligence. Phishing attacks rely on social engineering strategies to present deceptive links as trustworthy sources, deceiving individuals into sharing confidential data. Conclusion; This study explores the utilization of curated datasets and machine learning algorithms to develop adaptive and efficient phishing detection mechanisms, providing a robust defense against such malicious activities