Phishing Site Detection Using Machine Learning

Cybersecurity is greatly threatened by phishing attempts, which are becoming more complex on a regular basis. This study looks at how well different Machine Learning (ML) and Artificial Intelligence (AI) models identify phishing websites. Six models are assessed: Support Vector Machines, XG Boost, Random Forests, Decision Trees, Multilayer Perceptron’s, and Autoencoder Neural Networks. Each model’s performance is evaluated using F1 scores, accuracy, precision, and recall, which are based on a wide range of variables obtained via URL analysis. Our results highlight the advantages and disadvantages of each strategy by revealing significant variations in these models’ performances. By shedding light on the best machine learning techniques for phishing detection, this study advances cybersecurity by strengthening the arsenal of instruments against these malevolent endeavours.