AI Phishing Dataset for Model Training and Testing

A portfolio dataset uploaded by cont1n3nt for a GitHub project. It is intended for training and testing machine learning models, specifically in the context of AI phishing detection. The dataset was last updated on May 14, 2026.

Use Cases

• Training a binary classifier to detect phishing attempts based on features likely present in the data.
• Benchmarking model performance on a dedicated AI phishing task.
• Developing feature engineering techniques for cybersecurity applications.
• Educational demonstration of model training workflows for security datasets.

Strengths

• Dataset is explicitly intended for model training and testing, providing a clear purpose.
• The author and last update date (2026-05-14) are specified.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Created by author cont1n3nt for a GitHub portfolio project.

Freshness

Last updated 2026-05-14 12:17:07; freshness should be verified.