Phishing Website Detection
Rushikesh Sisode, Yash Mandlik, Tanmay Patil, Aryan Navale,
Student, Department of Computer Technology, Smt. Kashibai Navale College of Engineering,Vadgoan, SPPU, Maharashtra , India
Prof S. V. Tikore
Professor, Department of Computer Technology, Smt. Kashibai Navale College of Engineering ,Vadgoan, SPPU, Maharashtra , India
Abstract
Phishing attacks have become a major cybersecurity threat, targeting unsuspecting users by imitating legitimate websites to steal sensitive information. This project presents a robust phishing website detection system leveraging the Random Forest algorithm to accurately classify URLs as phishing or legitimate. The system architecture integrates the MERN stack for the user interface and backend processing, with Python handling machine learning tasks. Key stages include data preprocessing, feature extraction, and model training, focusing on URL characteristics like domain age, HTTPS usage, and website traffic. The Random Forest model offers high accuracy, robustness to noise, and interpretability through feature importance analysis. Hyperparameter tuning ensures optimal performance, while cross-validation minimizes overfitting. Real-time detection is achieved through seamless communication between frontend and backend, providing instant feedback to users. The system aims to strengthen cybersecurity by reducing false positives and ensuring adaptability against evolving phishing techniques. Future enhancements include expanding detection to other cyber threats and improving real-time processing. This solution sets a new standard for online safety, offering users greater confidence in their digital interactions.
Keywords:
Phishing Detection, Random Forest, Machine Learning, MERN Stack, URL Analysis, Cybersecurity, Feature Extraction, Real-Time Detection, Hyperparameter Tuning, Online Safety.
