Enhancing Online Safety: Phishing URL Detection Using Machine Learning and Explainable AI

With the rapid growth of the internet and online transactions, phishing attacks have become a prevalent cyber threat. Deceptive URLs are frequently used in phishing attempts to trick visitors into revealing sensitive information. In this study, ten machine learning methods were deployed namely, Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), K-Nearest Neighbors (KNN), Bernoulli Naïve Bayes (BNB), AdaBoost (AB), Neural Networks (NN) and Gradient Boosting (GB). The RF model had the highest accuracy of 98.55%. It is indeed, critical for users/ cybersecurity professionals to know exactly why a URL was flagged for phishing. This paper aims to detect phishing assaults using machine learning and Explainable AI (XAI). XAI- Shapely Additive Values (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) have been interpreted for the RF model to underline the features that drive the predictions.