Key points are not available for this paper at this time.
Phishing is the attempt to trick someone into disclosing confidential and private information by using internet communication, such as bank account details, passwords, credit/debit card details, and usernames. The accuracy of foreseeing such phishing assaults can be substantially enhanced through utilizing these algorithms. The primary objective of this research work is to enhance internet security by providing a dependable and productive method for detecting phishing websites. To achieve this, a machine learning-based approach was employed, utilizing various models trained on a dataset of phishing website attributes. The study evaluated a range of machine learning algorithms and classifiers, including Naive Bayes, Support Vector Machine, K-Nearest Neighbors, Gradient Boosting, Decision Tree, Random Forest, Bagging, Voting, and AdaBoost Classifiers. These evaluation parameters are used to determine the efficiency of the machine learning models including F1 Score, Accuracy, Precision, and Recall values. By training the dataset with key variables from credible websites, the Bagging Classifier algorithm demonstrated a substantial improvement, achieving an accuracy rate of 98.4% resulting in a significant enhancement in phishing website detection compared to other methods.
Sarvan et al. (Wed,) studied this question.