mlsanityData to 7 Oct 2026

A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems

arXiv 2408.03515 ↗First posted 7 Aug 2024cs.RO cs.AIcited by 15

On the map: LLM safety and security → Prompt injection and agent security

Abstract (arXiv)

The integration of Large Language Models (LLMs) like GPT-4o into robotic systems represents a significant advancement in embodied artificial intelligence. These models can process multi-modal prompts, enabling them to generate more context-aware responses. However, this integration is not without challenges. One of the primary concerns is the potential security risks associated with using LLMs in robotic navigation tasks. These tasks require precise and reliable responses to ensure safe and effective operation. Multi-modal prompts, while enhancing the robot's understanding, also introduce complexities that can be exploited maliciously. For instance, adversarial inputs designed to mislead the model can lead to incorrect or dangerous navigational decisions. This study investigates the impact of prompt injections on mobile robot performance in LLM-integrated systems and explores secure prompt strategies to mitigate these risks. Our findings demonstrate a substantial overall improvement of approximately 30.8% in both attack detection and system performance with the implementation of robust defence mechanisms, highlighting their critical role in enhancing security and reliability in mission-oriented tasks.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 21 of its 29 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

21 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defenses19 Oct
  2. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection23 Feb

Other references · 19

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  3. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  4. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  5. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  6. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  7. 2023Detecting Language Model Attacks with Perplexitycited by 411
  8. 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attentioncited by 375
  9. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 274
  10. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  11. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  12. 2023Effective Prompt Extraction from Language Modelscited by 83
7 more
  1. 2024Agent Planning with World Knowledge Modelcited by 66
  2. 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attackscited by 35
  3. 2024Prompting Techniques for Secure Code Generation: A Systematic Investigationcited by 33
  4. 2024Vocabulary Attack to Hijack Large Language Model Applicationscited by 12
  5. 2023A Survey on Prompting Techniques in LLMscited by 9
  6. 20243P-LLM: Probabilistic Path Planning using Large Language Model for Autonomous Robot Navigationcited by 8
  7. 2024How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?cited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 8.

15 papers.

Sort:

By area:

  1. 2024Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systemscited by 126
  2. 2024Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settingscited by 33
  3. 2025A Survey of Attacks on Large Language Modelscited by 13
  4. 2026Defense Against Indirect Prompt Injection via Tool Result Parsingcited by 8
  5. 2026What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?cited by 5
  6. 2026From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systemscited by 3
  7. 2025FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systemscited by 2
  8. 2025PD3F: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Modelscited by 1
  9. 2025Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safetycited by 1
  10. 2026RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robotscited by 1
  11. 2026When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systemscited by 1
  12. 2025Robustness of LLM-enabled vehicle trajectory prediction under data security threatscited by 0
3 more
  1. 2026A Sentence Relation-Based Approach to Sanitizing Malicious Instructionscited by 0
  2. 2026Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluationcited by 0
  3. 2026Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directionscited by 0