frangelbarrera/phishing-detection-rnn-cnn

Offline phishing detection model for websites using a hybrid CNN–LSTM architecture. Operates without internet access, classifying URLs as legitimate or potentially malicious based on learned patterns.

29
/ 100
Experimental

This tool helps identify malicious phishing websites by analyzing their URLs. You input a web address, and the system tells you if it's legitimate or a potential phishing threat, even without an internet connection. It's designed for anyone who needs to quickly verify URLs to protect themselves or their organization from online scams.

Use this if you frequently encounter suspicious links and need a quick, offline way to check if a URL is likely to be a phishing attempt.

Not ideal if you need absolute, flawless detection for all known threats, as this model may sometimes misclassify legitimate sites and should be supplemented with other security measures.

cybersecurity phishing-prevention web-safety scam-detection threat-intelligence
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/frangelbarrera/phishing-detection-rnn-cnn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.