SECURING CYBERSPACE: AN EFFICIENT MACHINE LEARNING BASED APPROACH TO PHISHING ATTACK DETECTION

We explore machine learning strategies and evaluate their viability in distinguishing characteristics that separate secure websites from phishing ones. Given the essential need to defend delicate information and maintain network integrity, we aim to determine the most proficient strategy for identifying phishing websites. Our research focuses on the Random Forest Classifier, illustrating its predominance over other strategies. We have achieved significant improvements in detection rates, with the Random Forest Classifier accomplishing an F1 score of 0.99, precision of 0.99, recall of 0.99, and an AUC of 1.00, outperforming other classifiers. By specifying each strategy and utilizing various assessment methods for visual performance representation, we provide a robust model for phishing detection.