Back to datasets
Dataset assetOpen Source CommunityCybersecurityIntrusion Detection
Jetlime/NF-UNSW-NB15-v2
The NF‑UNSW‑NB15‑v2 dataset is an extension of the UNSW‑NB15 dataset in NetFlow format, adding extra NetFlow features and labeling corresponding attack categories. It contains 2,390,275 flows, of which 95,053 (3.98%) are attack samples and 2,295,222 (96.02%) are benign. Attack samples are divided into nine sub‑categories: Fuzzers, Analysis, Backdoor, DoS, Exploits, Generic, Reconnaissance, Shellcode, and Worms. The dataset is primarily used for network‑traffic intrusion detection system research.
Source
hugging_face
Created
Nov 28, 2025
Updated
May 24, 2024
Signals
290 views
Availability
Linked source ready
Overview
Dataset description and usage context
Dataset Overview
Basic Information
- Dataset Name: NF-UNSW-NB15-v2
- Dataset Size: 100K < n < 1M
- Task Type: zero‑shot‑classification
- Number of Labels: 10
Content
- Total Flows: 2,390,275
- Attack Samples: 95,053 (3.98%)
- Benign Samples: 2,295,222 (96.02%)
- Attack Sub‑Categories: 9
Feature Information
- input: large string
- output: binary label
- Attack: multi‑class label including Analysis, Backdoor, Benign, DoS, Exploits, Fuzzers, Generic, Reconnaissance, Shellcode, Worms
- null_dask_index: int64 type
Splits
- Training Set: 2,270,761 samples, 2,311,136,604 bytes
- Test Set: 119,514 samples, 121,629,640 bytes
Download and Size
- Download Size: 431,370,947 bytes
- Dataset Size: 2,432,766,244 bytes
Usage
- Primary Use: NetFlow‑based intrusion detection systems
Structure
- Detailed Features: Includes IPV4_SRC_ADDR, IPV4_DST_ADDR and other flow‑related attributes
Citation
- BibTeX: see original
- APA: see original
Contact
- Maintainer: Mohanad Sarhan (m.sarhan@uq.net.au)
Need downstream help?
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.