Incorporating Machine Learning Algorithms to Detect Phishing Websites

Abstract

The emergence of smart cities and widespread acceptance of smart applications have altered our lives. The surge in internet usage has accelerated our transition into a cyberworld. While the Internet has become an indispensable part of our lives, security breaches like phishing websites have grown as a significant concern. It is an illegal action that involves tricking individuals & luring them to disclose their sensitive information, resulting in substantial financial loss or identity theft. Therefore, a dependable and consistent detection method for phishing websites is required. Due to the dynamic nature of machine learning, it has been widely utilized for distinguishing between phishing and legitimate sites. Hence, several Machine Learning techniques were examined as part of this research, including Gradient Boosting, K nearest neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Logistic Regression, and Decision Tree (DT). We evaluated the outcomes through model classification performance indicators. Each model was analyzed based on Accuracy Score, Precision, Recall & F-measure. Random Forest outperformed all other classifiers in terms of accuracy, achieving a score of 96.52% overall.