BadRobot: Jailbreaking Embodied LLMs in the Physical World
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913677513326592 |
|---|---|
| author | Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu |
| author_facet | Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu |
| contents | Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BadRobot, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge's flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BadRobot's attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BadRobot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20242 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BadRobot: Jailbreaking Embodied LLMs in the Physical World Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu Computers and Society Artificial Intelligence Robotics Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BadRobot, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge's flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BadRobot's attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BadRobot. |
| title | BadRobot: Jailbreaking Embodied LLMs in the Physical World |
| topic | Computers and Society Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2407.20242 |