Training a Machine Learning Model to detect a URL whether it is a phishing or Legitimate URL
- Collecting Data
- I have collected Phishing URLs from www.phishtank.org
- Legitimate URLs from Kaggle datasets
- Data Preprocessing
- Combining the phishing URLs and Legitimate URLs to make a complete dataset of URLs
- performed some data preprocessing techniques on that dataset
- Features Extraction
- Extracted many features that which makes that URLs Phishing or Legitimate from the URLs in the dataset
- By following the reasearch paper
- Model Selection