RTPS Attack Dataset Description

TL;DR

The paper presents a ROS2 RTPS attack dataset collected on a UGV testbed to study security vulnerabilities in RTPS DDS communications. It introduces two attack types, Command Injection and ARP Spoofing, with varying data collection times and rest periods, and details automated data collection and labeling procedures. The dataset comprises extensive robot and attack packet dumps along with labeled data to support anomaly detection and defense research for ROS2 networks and Fast-DDS. The work provides a concrete, reproducible resource for evaluating RTPS security and informs mitigation strategies for autonomous robotic systems.

Abstract

This paper explains all about our RTPS datasets. We collect malicious/benign packet data by injecting attack data in an Unmanned Ground Vehicle (UGV) in the normal state. We assembled the testbed, consisting of UGV, Controller, PC, and Router. We collect this dataset in the UGV part of our testbed. We conducted two types of attack "Command Injection" and "Command Injection with ARP Spoofing" on our 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 to contribute to the development of defense technologies like anomaly detection to address security threat issues in ROS2 networks and Fast-DDS implements.

Figures (10)

• Figure 1: Structure of the testbed for dataset Collection
• Figure 2: Stella N1 stella_n1_image
• Figure 3: Stella N1 block diagram stella_block_diagram
• Figure 4: Two types of attacks on dataset
• Figure 5: Difference between regular and ARP Spoofing Communication arp_spoofing