具身人工智能的安全性：风险、攻击与防御综述
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
AI总结：
本文综述了具身AI在感知、认知、规划、行动及交互全流程中的安全风险、攻击与防御方法，提出了多层次分类体系，并指出了多模态感知融合脆弱性、规划不稳定及人机交互可信度等关键挑战。
摘要：
具身人工智能将感知、认知、规划与交互集成到在开放、安全关键环境中运行的智能体中。随着这些系统获得自主性并进入交通、医疗、工业或辅助机器人等领域，确保其安全性在技术上具有挑战性，在社会上也变得不可或缺。与数字AI系统不同，具身智能体必须在不确定的感知、不完整的知识和动态的人机交互下行动，故障可能直接导致物理伤害。本综述对具身AI中的安全研究进行了全面且结构化的回顾，考察了从感知、认知到规划、行动与交互以及智能体系统的完整具身流程中的攻击与防御。我们引入了一个多层次分类体系，统一了分散的研究工作，并将具身特定的安全发现与视觉、语言和多模态基础模型的更广泛进展联系起来。我们的综述综合了来自500多篇论文的见解，涵盖对抗性攻击、后门攻击、越狱攻击和硬件级攻击；攻击检测、安全训练和鲁棒推理；以及风险感知的人机交互。这一分析揭示了几个被忽视的挑战，包括多模态感知融合的脆弱性、越狱攻击下规划的不稳定性，以及开放场景中人机交互的可信度。通过将领域组织成连贯的框架并识别关键研究空白，本综述为构建不仅具备能力和自主性，而且在现实部署中安全、鲁棒和可靠的具身智能体提供了路线图。
英文摘要：
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as transportation, healthcare, and industrial or assistive robotics, ensuring their safety becomes both technically challenging and socially indispensable. Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions, where failures can directly lead to physical harm. This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system. We introduce a multi-level taxonomy that unifies fragmented lines of work and connects embodied-specific safety findings with broader advances in vision, language, and multimodal foundation models. Our review synthesizes insights from over 500 papers spanning adversarial, backdoor, jailbreak, and hardware-level attacks; attack detection, safe training and robust inference; and risk-aware human-agent interaction. This analysis reveals several overlooked challenges, including the fragility of multimodal perception fusion, the instability of planning under jailbreak attacks, and the trustworthiness of human-agent interaction in open-ended scenarios. By organizing the field into a coherent framework and identifying critical research gaps, this survey provides a roadmap for building embodied agents that are not only capable and autonomous but also safe, robust, and reliable in real-world deployment.
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。
