Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety
2025/09/02 by Zhang, Wenxiao, Kong, Xiangrui, Dewitt, Conan +2 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Robotics (cs.RO)
paper · doi:10.48550/arxiv.2509.02163
Abstract
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/
Citations
- Safety Guardrails for LLM-Enabled Robots
- Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
- Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
- KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
- ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
- A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
- Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
- Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency
- LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
- Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
- From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
- How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?
- LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding
- Foundation Models in Robotics: Applications, Challenges, and the Future
- A Survey on Prompting Techniques in LLMs
- PaLM-E: An Embodied Multimodal Language Model
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
- BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
- Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
- A Survey of Embodied AI: From Simulators to Research Tasks
- On the Vulnerability of LLM/VLM-Controlled Robotics
- A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
Cited by
Related