• Pratyush Kala
• Amita Goel

This study applies machine learning (ML) and deep learning (DL) techniques to detect phishing websites in real time through a Chrome extension. Traditional phishing detectors are often web-based, requiring users to copy and paste URLs manually, which limits usability. A dataset from Kaggle with lexical, domain-based, and content features was used to train and evaluate more than 12 models, including Logistic Regression, SVC, Random Forest, Gradient Boosting, CatBoost, XGBoost, and MLP, with hyperparameter tuning via GridSearchCV. Results show that the Gradient Boosting Classifier (GBC) achieved the highest accuracy of 97%, outperforming other models in precision and recall. The final model was deployed with a FastAPI backend and integrated into a Chrome extension for seamless, real-time URL classification. The findings demonstrate the effectiveness of ensemble ML methods for phishing detection and highlight the practicality of browser-based security tools.

Phishing Detection, Chrome Extension, Machine Learning, Deep Learning, Gradient Boosting Classifier, Cybersecurity, Real-Time Detection, FastAPI, Browser Security

"Phishing Detector Chrome Extension", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.c568-c573, November-2025, Available :http://www.jetir.org/papers/JETIR2511268.pdf

"Phishing Detector Chrome Extension", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppc568-c573, November-2025, Available at : http://www.jetir.org/papers/JETIR2511268.pdf