QGAN-NAD provides 5 normalized network traffic datasets prepared for quantum machine learning baselines. The datasets are preprocessed and ready for immediate use. Details on the creator, size, and update date are not available.
Use Cases
- Train quantum generative adversarial networks (QGANs) for anomaly detection using normalized traffic features.
- Benchmark quantum classification algorithms against classical methods on preprocessed network traffic data.
- Develop hybrid quantum-classical models for intrusion detection using the provided normalized datasets.
Strengths
- Contains 5 distinct datasets for varied benchmarking.
- Data is pre-normalized, reducing initial preprocessing effort.
Limitations
- Dataset size, row count, and feature details are unknown.
- Lack of metadata limits understanding of data origin and potential biases.
Provenance
- Source
- null
- Collection Method
- Network traffic data, normalized for quantum machine learning applications.
- Time Range
- null
- Freshness
- null
- Geography
- null