Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911134083186688 |
|---|---|
| author | Zhang, Wenxiao Kong, Xiangrui Dewitt, Conan Bräunl, Thomas Hong, Jin B. |
| author_facet | Zhang, Wenxiao Kong, Xiangrui Dewitt, Conan Bräunl, Thomas Hong, Jin B. |
| contents | Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against adversarial attacks and safety in complex environments, remains a critical challenge. To address this, we propose a unified framework that mitigates prompt injection attacks while enforcing operational safety through robust validation mechanisms. Our approach combines prompt assembling, state management, and safety validation, evaluated using both performance and security metrics. Experiments show a 30.8% improvement under injection attacks and up to a 325% improvement in complex environment settings under adversarial conditions compared to baseline scenarios. This work bridges the gap between safety and security in LLM-based robotic systems, offering actionable insights for deploying reliable LLM-integrated mobile robots in real-world settings. The framework is open-sourced with simulation and physical deployment demos at https://llmeyesim.vercel.app/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02163 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety Zhang, Wenxiao Kong, Xiangrui Dewitt, Conan Bräunl, Thomas Hong, Jin B. Robotics Artificial Intelligence Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against adversarial attacks and safety in complex environments, remains a critical challenge. To address this, we propose a unified framework that mitigates prompt injection attacks while enforcing operational safety through robust validation mechanisms. Our approach combines prompt assembling, state management, and safety validation, evaluated using both performance and security metrics. Experiments show a 30.8% improvement under injection attacks and up to a 325% improvement in complex environment settings under adversarial conditions compared to baseline scenarios. This work bridges the gap between safety and security in LLM-based robotic systems, offering actionable insights for deploying reliable LLM-integrated mobile robots in real-world settings. The framework is open-sourced with simulation and physical deployment demos at https://llmeyesim.vercel.app/ |
| title | Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.02163 |