Zero-Day Phishing: Labeled Post-Rendered HTML Pages

Labeled HTML pages categorized as benign or phishing for training cybersecurity machine learning models. The dataset is hosted on Kaggle, but the author, organization, and creation date are unspecified. The total number of pages, file formats, and specific features are unknown.

Use Cases

• Train binary classifiers to distinguish phishing from benign websites based on HTML content.
• Develop feature extraction pipelines for post-rendered web page analysis.
• Benchmark model performance on a labeled corpus of HTML pages for cybersecurity applications.

Strengths

• Data is explicitly labeled for a binary classification task (benign vs. phishing).
• Focuses on post-rendered HTML, which likely captures the final content a user sees.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle