Skip to content

Dataset · zefang-liu

Email database for phishing detection

zefang-liu/phishing-email-dataset

English email dataset for training and testing phishing filters.

What's inside

Contains English email texts for classification into phishing and legitimate categories. The corpus size ranges from 10,000 to 100,000 records. The dataset is a direct copy of the Phishing Email Detection dataset from Kaggle by user Cyber Cop and is distributed under the GNU LGPL 3.0 license.

What you can do with it

  • Training a classifier for filtering phishing campaigns
  • Testing corporate email security systems
  • Fine-tuning compact text models for fraud detection
Tasks
Text classification
Languages
English
Size
10K–100K rows
Downloads this month
2K
Likes
40

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("zefang-liu/phishing-email-dataset")