A comparison study of machine learning techniques for phishing detection

Abstract

In the last few years, phishing attacks have been increasing eventually. As the internet is developing, security for it is becoming a challenging task. Cyber-attacks and threats are increasing rapidly. These days many fake websites are created to deceive victims by collecting their login credentials, bank details, etc. Many anti-phishing products are launched into the market and use blacklists, heuristics, and visual and machine learning-based approaches, these products cannot prevent all the phishing attacks. However, unlike predicting phishing URLs, there are only a few studies that compare machine learning techniques in predicting phishing. The present study compares the predictive accuracy of several machine learning methods including Decision tree, Random forest, Multilayer Perceptions, Support Vector Machines, and XGBoost for predicting phishing URLs.