paperDecember 2025Unreviewed

Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges

Xinyu Huang, B. ShyamKarthickV, Taozhao Chen, Mitch Bryson, Thomas L. Chaffey, Huaming Chen, Kim-Kwang Raymond Choo, Ian R. Manchester, S. Karthick

arXiv.org

View resource

Abstract

The integration of Large Language Models (LLMs) into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities stemming from the''embodiment gap'', a discord between the LLM's abstract reasoning and the physical, context-dependent nature of robotics. While security for text-based LLMs is an active area of research, existing solutions are often insufficient to address the

Cite

@misc{huang2025trust,
  title = {{Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges}},
  author = {Xinyu Huang and B. ShyamKarthickV and Taozhao Chen and Mitch Bryson and Thomas L. Chaffey and Huaming Chen and Kim-Kwang Raymond Choo and Ian R. Manchester and S. Karthick},
  year = {2025},
  month = dec,
  eprint = {2601.02377},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2601.02377},
  url = {https://www.semanticscholar.org/paper/71f30c8b6aca4dbd4a81302ac30335421b1a8688}
}