Malicious NPM Package and Phishing URL Detection Dataset

A cybersecurity dataset for detecting malicious software packages and phishing URLs. The description suggests it is intended for use with deep learning models. The dataset's size, origin, and specific features are not detailed in the provided metadata.

Use Cases

• Training a classifier to identify malicious NPM packages based on package metadata or code features.
• Developing a model to detect phishing URLs based on textual or structural URL characteristics.
• Benchmarking deep learning architectures for cybersecurity text classification tasks.

Strengths

• Focuses on a high-impact domain in software supply chain security.
• Platform tags indicate applicability for text classification and natural language processing tasks.

Limitations

• Row count and dataset scale are 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