RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots

Abstract

We present RIPA, the first systematic multi-channel empirical study of prompt injection attacks delivered through the sensory pipeline of a ROS 2-based LLM-controlled robotic system. Across 100 independent runs per injection variant on five LLMs spanning four model families and parameter scales from approximately 4B to approximately 284B (DeepSeek-V4-Flash, Llama-3-8B-Instruct-Lite, Llama-3.3-70B-Instruct-Turbo, Qwen 2.5-7B-Instruct-Turbo, Gemma-3n-E4B), we identify model-specific vulnerability

Categories

Framework mappings

Suggested from the entry's categories.

@misc{dorzhiev2026ripa,
  title = {{RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots}},
  author = {Nima Dorzhiev},
  year = {2026},
  month = jun,
  eprint = {2606.28649},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.28649}
}