Robo-Troj: Attacking LLM-based Task Planners
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_ | 1866912394272309248 |
|---|---|
| author | Nahian, Mohaiminul Al Altaweel, Zainab Reitano, David Ahmed, Sabbir Zhang, Shiqi Rakin, Adnan Siraj |
| author_facet | Nahian, Mohaiminul Al Altaweel, Zainab Reitano, David Ahmed, Sabbir Zhang, Shiqi Rakin, Adnan Siraj |
| contents | Robots need task planning methods to achieve goals that require more than individual actions. Recently, large language models (LLMs) have demonstrated impressive performance in task planning. LLMs can generate a step-by-step solution using a description of actions and the goal. Despite the successes in LLM-based task planning, there is limited research studying the security aspects of those systems. In this paper, we develop Robo-Troj, the first multi-trigger backdoor attack for LLM-based task planners, which is the main contribution of this work. As a multi-trigger attack, Robo-Troj is trained to accommodate the diversity of robot application domains. For instance, one can use unique trigger words, e.g., "herical", to activate a specific malicious behavior, e.g., cutting hand on a kitchen robot. In addition, we develop an optimization method for selecting the trigger words that are most effective. Through demonstrating the vulnerability of LLM-based planners, we aim to promote the development of secured robot systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robo-Troj: Attacking LLM-based Task Planners Nahian, Mohaiminul Al Altaweel, Zainab Reitano, David Ahmed, Sabbir Zhang, Shiqi Rakin, Adnan Siraj Robotics Artificial Intelligence Robots need task planning methods to achieve goals that require more than individual actions. Recently, large language models (LLMs) have demonstrated impressive performance in task planning. LLMs can generate a step-by-step solution using a description of actions and the goal. Despite the successes in LLM-based task planning, there is limited research studying the security aspects of those systems. In this paper, we develop Robo-Troj, the first multi-trigger backdoor attack for LLM-based task planners, which is the main contribution of this work. As a multi-trigger attack, Robo-Troj is trained to accommodate the diversity of robot application domains. For instance, one can use unique trigger words, e.g., "herical", to activate a specific malicious behavior, e.g., cutting hand on a kitchen robot. In addition, we develop an optimization method for selecting the trigger words that are most effective. Through demonstrating the vulnerability of LLM-based planners, we aim to promote the development of secured robot systems. |
| title | Robo-Troj: Attacking LLM-based Task Planners |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17070 |