PROTEA：保障机器人任务规划与执行的安全性
PROTEA: Securing Robot Task Planning and Execution
AI总结：
PROTEA通过LLM-as-a-Judge机制评估机器人任务计划的安全性，解决维度和历史挑战，提升任务规划系统的鲁棒性和安全性。
摘要：
机器人需要任务规划方法来为复杂任务生成动作序列。最近关于对抗攻击的研究揭示了现有机器人任务规划器存在显著漏洞，尤其是基于基础模型构建的规划器。本文旨在通过引入PROTEA，一种LLM-as-a-Judge防御机制，来评估任务计划的安全性。PROTEA旨在解决计划安全评估中的维度和历史挑战。我们使用不同的LLM实现了多个PROTEA版本进行比较。为系统评估，我们创建了一个包含良性与恶意任务计划的数据集，其中恶意行为在不同级别的隐蔽性下被注入。我们的结果为寻求增强其任务规划系统鲁棒性和安全性的机器人系统从业者提供了可操作的见解。详情、数据集和演示见：https://protea-secure.github.io/PROTEA/
英文摘要：
Robots need task planning methods to generate action sequences for complex tasks. Recent work on adversarial attacks has revealed significant vulnerabilities in existing robot task planners, especially those built on foundation models. In this paper, we aim to address these security challenges by introducing PROTEA, an LLM-as-a-Judge defense mechanism, to evaluate the security of task plans. PROTEA is developed to address the dimensionality and history challenges in plan safety assessment. We used different LLMs to implement multiple versions of PROTEA for comparison purposes. For systemic evaluations, we created a dataset containing both benign and malicious task plans, where the harmful behaviors were injected at varying levels of stealthiness. Our results provide actionable insights for robotic system practitioners seeking to enhance robustness and security of their task planning systems. Details, dataset and demos are provided: https://protea-secure.github.io/PROTEA/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
