An Efficient Phishing Website Detection Plugin Service Based on Website Trustworthiness Evaluation

Phishing attacks remain a significant threat to online users, and existing anti-phishing mechanisms often fall short in providing real-time, adaptive protection. This study proposes a browser extension that leverages machine learning to assess website trustworthiness and detect phishing threats in real time. A logistic regression classifier was trained using axx dataset comprising both legitimate and phishing URLs sourced from PhishTank and Google’s site rankings. The model achieved an accuracy of 0.96 on training data and 0.91 on test data. Our browser extension provides a robust, real-time defense against phishing, with minimal latency and a user-friendly interface.