albahnsen / deepphish_blackhat_demo Goto Github PK

Hello, sorry as this is probably the wrong place for this but I couldn't find your email.

Do you have the dataset used for your paper Classifying phishing URLs using recurrent neural networks available online anywhere?

I think it's 1 million malicious URLs from PhishTank and 1 million harmless URLs from CommonCrawl.

I want to compare your method with 2 others I found which use feature extraction and getting the data seems like it will be a big task based on size.