Gotham 2025: Large-Scale IoT Network Traffic for Intrusion Detection

A large-scale dataset of IoT network traffic intended for intrusion detection research. The dataset is hosted on Kaggle, but its author, organization, and specific collection details are not provided. The description indicates it is a master CSV file, likely containing tabular network flow or packet data.

Use Cases

• Train machine learning models for anomaly detection based on network traffic patterns.
• Benchmark the performance of different intrusion detection algorithms on IoT-specific traffic.
• Analyze attack patterns and vulnerabilities in simulated or real IoT network environments.

Strengths

• The dataset is described as 'large-scale', suggesting a substantial volume of data for model training.
• It is specifically designed for the research domain of IoT network security and intrusion detection.

Limitations

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

Provenance

Source

Kaggle