Phishing-URL-Detection and Phishing-detector

These are competitors—both tools solve the identical problem of detecting phishing URLs through visual and semantic analysis, so users would choose one or the other rather than use both together.

Phishing-detector
27
Experimental
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 24/25
Maintenance 0/25
Adoption 7/25
Maturity 1/25
Community 19/25
Stars: 218
Forks: 117
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
Stars: 25
Forks: 17
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
No License Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About Phishing-URL-Detection

vaibhavbichave/Phishing-URL-Detection

Phishers use the websites which are visually and semantically similar to those real websites. So, we develop this website to come to know user whether the URL is phishing or not before using it. URL - http://phishing-url-detector-api.herokuapp.com/

Leverages ensemble machine learning models (Gradient Boosting, CatBoost, XGBoost) trained on URL structural features like HTTPS usage, anchor URLs, and website traffic patterns to achieve 97.4% classification accuracy. Built with Flask for the web interface and scikit-learn for model training, the system extracts feature vectors from submitted URLs and uses a pickled Gradient Boosting classifier for real-time predictions.

About Phishing-detector

asrith-reddy/Phishing-detector

Phishers use the websites which are visually similar to those real websites. So, we developed this website so that user can know whether the URL is phishing or not before using it. URL -

Scores updated daily from GitHub, PyPI, and npm data. How scores work