Iman Akour, Noha Alnazzawi, Ahmad Aburayya, Raghad Alfaisal & Said A. Salloum
Phishing is one of the various types of internet frauds that many people fall victim to. Scammers use phishing attacks to gain access to a user's sensitive information. This is done by creating fake websites that appear to be legitimate websites belonging to prestigious organizations. As a result, there is an urgent need to conduct research on the phenomenon of phishing attacks, which will prove extremely beneficial to individuals working in cyber security and phishing attack prevention firms. Blacklisting websites, retrieving characteristics from a website, raising awareness amongst people, and drawing parallels between phishing attacks and known patterns of prior phishing attacks are some of the ways currently used for detecting phishing attacks. To analyze and classify phishing websites, this paper employs classification models. The classification models are created by extracting phishing website features. The model was trained using machine learning algorithms such as “Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), and NAÏVE BAYES (NB)”classifiers on two different datasets containing 58,645 and 88,647 websites identified as phishing and legitimate URLs, respectively. SVM was discovered to be the best algorithm for the detection of phishing URLs, showing a degree of accuracy of 96.30 percent.