We collect attack and normal packet data by injecting attack data in an Unmanned Ground Vehicle (UGV) which is normal state.

To collect this dataset, We assembled a test bed consisting of UGV, controller, PC, and router. We conducted two types of Attacks "Command Injection" and "ARP Spoofing" on the testbed.

The data collection time is 180, 300, 600, and 1200, the scenario has 30 each on collection time. 240 total. We expect this dataset will contribute to the development of technologies such as anomaly detection to address security threat issues in ROS2 networks and UGVs.

If you want to know more information about this dataset, please refer to our description paper below.


Please leave citations in your results if you want to use this dataset. 

There are dataset descryption papers written in both languages.

Korean Version (국문): Download

English Version (영문): Will be updated...


The data set consists of the packet data file (.pcap) and the label file (.csv).

3-1. Attack Packet Data (.pcap)

Attack packet data contains attack and normal packet data during the collection time mentioned above. There are two types of .pcap files on the dataset, "_labeled_[Number].pcap" is collected on the attacker's side, and ".pcap" is collected on the defender's side. Attack packet data files consist of ".pcap" files which easily get raw packet data.

3-2. Label Data (.csv)

Label data contains information that may help detect both types of anomaly, "Command Injection" and "ARP Spoofing". It contains Time, IP address, MAC address, some values in RTPS and ARP, and labeling data of both attacks. These files are examples of labeling of the dataset.


We share datasets for both academic and non-commercial purposes only. Also, This dataset follows "CC BY-NC" Creative Commons Licenses. More information about the license: https://creativecommons.org/licenses/by-nc/4.0/

Download Link: Download


We welcome your feedback or comments. Leave a message freely.

Dong Young Kim (klgh1256@korea.ac.kr), Huy Kang Kim (cenda@korea.ac.kr


This work was supported by the Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT). 

(Grant No. 2020-0-00374, Development of Security Primitives for Unmanned Vehicles).