Phishing Email and URL Detection Dataset with 200k Samples

200,000 entries combine email messages and URLs for multi-class phishing detection. The dataset, created by cybersectony, contains 22,644 email samples and 177,356 URL samples, each with a content and label field. It was last updated on Hugging Face in October 2024.

Use Cases

• Train a text classifier to predict the phishing label from email content.
• Build a URL classifier using the content field containing URL strings and their corresponding labels.
• Analyze feature patterns distinguishing between the four label classes (0, 1, 2, 3) within the content.
• Benchmark multi-class classification models on a mixed dataset of email and URL text data.

Strengths

• 200,000 total samples provide a substantial volume for model training.
• Clear split between 22,644 email and 177,356 URL samples allows for focused analysis.

Limitations

• Class distribution for the four labels (0, 1, 2, 3) is not specified, risking potential imbalance.
• The dataset combines two distinct data types (emails and URLs) which may require separate preprocessing pipelines.

Provenance

Source

Hugging Face dataset uploaded by author 'cybersectony'.

Collection Method

Combined collection of email messages and URLs, methodology not detailed.

Freshness

Last updated on the platform in October 2024.