Phishing attack detection using machine learning

Abstract

Phishing is a typical type of cyber-attack in which attackers attempt to trick users by creating fake websites or sending misleading emails. These fake platforms often look very similar to genuine ones, making it difficult for users to identify them. As a result, people may unintentionally divulge private information, such credit card numbers or passwords.. Traditional detection methods like blacklist-based systems are not very effective, as new phishing websites are continuously created and updated. To address this issue, machine learning techniques have been widely explored. In this paper, various studies related to phishing detection using models including Random Forest, Decision Tree, Support Vector Machine (SVM), and deep learning techniques. Most of these methods use features based on URL structure, domain information, and webpage content. However, it is observed that different studies use different datasets and evaluation metrics, which makes comparison difficult. Additionally, challenges such as detecting new types of phishing attacks and achieving real-time performance still exist. Therefore, combining multiple approaches and adopting a common evaluation framework may help improve the effectiveness of phishing detection systems