- Extracts 30 features from URLs to train a classifier. Analyzed the distinct characteristics of phishing URLs and their differentiation from legitimate URLs based on the Phishing Websites Features study.
- Collected and preprocessed a dataset with over 11,000 rows from Kaggle for training and evaluation purposes.
- Implemented and evaluated the K-Nearest Neighbors (KNN) algorithm for classification tasks, achieving accurate results.
- Developed a user-friendly application that can assist users in identifying phishing URLs.
Â
Live demo: https://phishing-url-knn.streamlit.app
Algorithm Evaluation: https://colab.research.google.com/drive/1MjMIZnLxSrJfil_qf6rxAufm63rLPdrG
Â