SoK: Security and Privacy of Foundation-Model-Powered Robots

📄 arXiv: 2606.16788v1 📥 PDF

作者: Xueluan Gong, Chen Chen, Jinxin Liu, Qian Wang, Kwok-Yan Lam

分类: cs.RO

发布日期: 2026-06-15

备注: 21 pages, 2 figures


💡 一句话要点

提出F-E-S-G框架以解决基础模型驱动机器人安全与隐私问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 基础模型 安全与隐私 机器人技术 风险分析 多层次分类 治理影响 生态系统

📋 核心要点

  1. 现有文献对基础模型驱动机器人安全与隐私的分析缺乏统一结构,难以全面识别风险来源及传播路径。
  2. 本文提出F-E-S-G框架,系统分析基础模型驱动机器人在安全与隐私方面的风险,涵盖四个层次。
  3. 通过对96篇文献的系统化分析,揭示了多种威胁模式和防御不匹配,指出了未来研究的开放挑战。

📝 摘要(中文)

基础模型正在重塑机器人技术,使其能够理解开放式指令、在多模态环境中推理并在复杂的开放世界中操作。然而,这种集成也引入了超出基础模型本身的安全与隐私风险。现有文献往往集中于特定的基础模型类型、风险类别或缓解策略,缺乏统一的结构来分析风险的来源及其在机器人系统中的传播。为此,本文提出了一个渐进的F-E-S-G结构边界框架,涵盖基础模型层、具身系统层、支持生态系统层和治理影响层,并基于此结构开发了多层次分类法,系统化了96篇相关文献,揭示了多种威胁模式和防御不匹配现象,指出了未来研究的挑战与方向。

🔬 方法详解

问题定义:本文旨在解决基础模型驱动机器人在安全与隐私方面的风险分析缺乏统一结构的问题。现有方法往往局限于特定类型或类别,无法全面识别和分析风险的传播。

核心思路:提出F-E-S-G结构边界框架,涵盖基础模型、具身系统、支持生态系统和治理影响四个层次,以系统化地分析安全与隐私风险。

技术框架:框架分为四个层次:基础模型层(F)、具身系统层(E)、支持生态系统层(S)和治理影响层(G)。在此基础上,构建多层次分类法,组织现有研究。

关键创新:最重要的创新在于提出了F-E-S-G框架,能够全面分析风险的来源及其在机器人系统中的传播,填补了现有文献的空白。

关键设计:在分类过程中,使用了细粒度编码属性,包括目标、生命周期阶段、机制、系统访问和效果等,以便更好地组织和分析文献。

🖼️ 关键图片

fig_0
fig_1

📊 实验亮点

通过对96篇文献的系统化分析,揭示了多种威胁模式和防御不匹配现象,为未来研究提供了明确的方向和挑战,推动基础模型驱动机器人技术的安全与隐私保护。

🎯 应用场景

该研究的潜在应用领域包括智能机器人、自动驾驶、无人机等,能够为这些系统的安全与隐私保护提供理论基础和实践指导,促进技术的负责任发展。

📄 摘要(原文)

Foundation models are reshaping robotics by enabling robots to interpret open-ended instructions, reason over multimodal contexts, and operate in complex, open-world environments. However, their integration also introduces security and privacy (S&P) risks that extend beyond the FMs themselves to embodied execution pipelines, supporting ecosystems, and broader governance impacts. Existing literature reviews provide valuable insights but often focus on specific FM types, risk categories, mitigation strategies, or trust boundaries. Consequently, the field lacks a unified structure for analyzing where risks originate, how they propagate across robotic systems, and where mitigations should intervene. To address this gap, we propose a progressive F-E-S-G structural boundary framework for analyzing the S&P of FM-powered robots. The framework comprises four layers: the Foundation model layer (F), Embodied system layer (E), Supporting ecosystem layer (S), and Governance impact layer (G). Building on this structure, we develop a multi-level taxonomy that organizes prior studies along three levels: F-E-S-G trust boundary, security-privacy concerns, and risk-mitigation perspectives. We further annotate each study using fine-grained coding attributes, including target, lifecycle stage, mechanism, system access, and effect. Guided by this framework and taxonomy, we systematize 96 papers. Our analysis uncovers multiple threat patterns, defense mismatches, and evaluation gaps that are difficult to identify from a single-boundary perspective. Based on these findings, we identify open challenges and future directions to provide a research agenda for developing secure, privacy-preserving, and responsibly governed FM-powered robotic systems.