From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems

Mingyang Xie, Jin Wei-Kocsis

Abstract

The integration of large language models (LLMs) into robotic control pipelines enables natural language interfaces that translate user prompts into executable commands. However, this digital-to-physical interface introduces a critical and underexplored vulnerability: structured backdoor attacks embedded during fine-tuning. In this work, we experimentally investigate LoRA-based supply-chain backdoors in LLM-mediated ROS2 robotic control systems and evaluate their impact on physical robot executio

Categories

Cite This Resource

@article{llmsec202600153,
  title = {From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems},
  author = {Mingyang Xie and Jin Wei-Kocsis},
  year = {2026},
  url = {https://arxiv.org/abs/2604.03890},
}