pcy12345BSU/UNSW-NB15

---
license: other
task_categories:
- tabular-classification
tags:
- intrusion-detection
- network-security
- cybersecurity
- IDS
- UNSW-NB15
- anomaly-detection
pretty_name: UNSW-NB15 Network Intrusion Detection Dataset
size_categories:
- 100K<n<1M
---

# UNSW-NB15 Network Intrusion Detection Dataset

## Description

The UNSW-NB15 dataset was created by the Cyber Range Lab of the Australian Centre
for Cyber Security (ACCS) at the University of New South Wales (UNSW). It contains
a hybrid of real modern normal activities and synthetic contemporary attack behaviours.

The raw network packets were captured using the IXIA PerfectStorm tool to generate
9 types of attacks: Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic,
Reconnaissance, Shellcode, and Worms.

## Dataset Details

- **Source**: University of New South Wales (UNSW), Australia
- **Year**: 2015
- **Features**: 49 features including flow-based and packet-based attributes
- **Attack Types**: 9 categories (Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnaissance, Shellcode, Worms)
- **Total Records**: ~2.5 million
- **Training Set**: 175,341 records
- **Testing Set**: 82,332 records

## Citation

```bibtex
@article{moustafa2015unsw,
title={UNSW-NB15: a comprehensive data set for network intrusion detection systems},
author={Moustafa, Nour and Slay, Jill},
journal={Military Communications and Information Systems Conference (MilCIS)},
year={2015},
publisher={IEEE}
}
```

## License

This dataset is provided for research and educational purposes.
Please cite the original paper when using this dataset.

## Original Source

- https://research.unsw.edu.au/projects/unsw-nb15-dataset