Phishing website classifier

The brief

Students and staff at a college keep receiving links to fake login pages. The IT cell wants a checker that scores a website as likely phishing or safe, and says which signs gave it away. Good looks like: high recall on phishing sites, a clear reason for each verdict, and a simple page where anyone can paste a link.

What you will build

1. Explore the features and how they relate to phishing
2. Train and compare logistic regression, random forest and gradient boosting
3. Explain each prediction with feature importance or SHAP
4. Build a small web form that scores a link
5. Write up what attackers do that the model learns

Free, open data to build it with

• Phishing Websites ↗ UCI Machine Learning Repository

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.