UNSQ-NB15
UNSW-NB15 is a network intrusion dataset. It contains nine different attacks, includes DoS, worms, Backdoors, and Fuzzers. The dataset contains raw network packets. The number of records in the training set is 175,341 records and the testing set is 82,332 records from the different types, attack and normal.
Source: Evaluation of Adversarial Training on Different Types of Neural Networks in Deep Learning-based IDSs
Image Source: https://www.unsw.adfa.edu.au/unsw-canberra-cyber/cybersecurity/ADFA-NB15-Datasets/
Paper: UNSW-NB15: a comprehensive data set for network intrusion detection systems
Variants: UNSW-NB15
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Synthetic Data Generation | kiNETGAN | KiNETGAN: Enabling Distributed Network Intrusion … | 2024-05-26 |
| Synthetic Data Generation | CTGAN | KiNETGAN: Enabling Distributed Network Intrusion … | 2024-05-26 |
| Intrusion Detection | MSTREAM-AE | MSTREAM: Fast Anomaly Detection in … | 2020-09-17 |
Recent papers with results on this dataset: