This project aims to detect phishing URLs using machine learning techniques. Phishing is a fraudulent attempt to obtain sensitive information by disguising as a trustworthy entity in electronic communications. This project leverages Python and various machine learning algorithms to identify and classify phishing URLs.
Data Collection: Gather a dataset of URLs labeled as phishing or legitimate. Feature Extraction: Extract relevant features from URLs, such as length, presence of special characters, and domain age. Model Training: Train machine learning models like Decision Trees, Random Forests, and Support Vector Machines to classify URLs. Evaluation: Evaluate the models using metrics like accuracy, precision, recall, and F1-score. Deployment: Implement the trained model in both desktop and web applications.
Desktop Application: A Python Tkinter-based application for detecting phishing URLs. Web Application: A CGI-based web application for real-time phishing URL detection.
A demo video and documentation is included to explain and showcase the functionality and usage of both the desktop and web applications.