幻影威胁：探索和增强VLA模型对物理传感器攻击的鲁棒性
Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
AI总结：
本文提出了一种新型框架，用于研究和增强VLA模型对物理传感器攻击的鲁棒性，并开发了对抗训练方法以提升模型安全性。
摘要：
视觉-语言-动作（VLA）模型通过启用端到端的感知到行动管道，革新了机器人系统，该管道整合了多种感觉模态，如由摄像头处理的视觉信号和由麦克风捕获的听觉信号。这种多模态整合使VLA模型能够利用多样化的传感器数据流来解释复杂的现实世界环境。鉴于VLA系统严重依赖于感觉输入，VLA模型对物理世界传感器攻击的安全性仍严重缺乏研究。为了解决这一差距，我们首次系统地研究了针对VLA的物理传感器攻击，量化了传感器攻击的影响，并调查了VLA模型的防御措施。我们引入了一个新的“真实-仿真-真实”框架，自动模拟基于物理的传感器攻击向量，包括六个针对摄像头和两个针对麦克风的攻击，并在真实机器人系统上验证了它们。通过在各种VLA架构和任务上进行大规模评估，在不同的攻击参数下，我们展示了显著的漏洞，这些漏洞模式揭示了任务类型和模型设计的关键依赖性。我们进一步开发了一种基于对抗训练的防御方法，该方法在不损害模型性能的情况下，增强了VLA对由传感器攻击引起的非分布物理扰动的鲁棒性。我们的发现暴露了对标准化鲁棒性基准和缓解策略的紧迫需求，以确保VLA在安全关键环境中部署的安全性。
英文摘要：
Vision-Language-Action (VLA) models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA models to interpret complex, real-world environments using diverse sensor data streams. Given the fact that VLA-based systems heavily rely on the sensory input, the security of VLA models against physical-world sensor attacks remains critically underexplored. To address this gap, we present the first systematic study of physical sensor attacks against VLAs, quantifying the influence of sensor attacks and investigating the defenses for VLA models. We introduce a novel "Real-Sim-Real" framework that automatically simulates physics-based sensor attack vectors, including six attacks targeting cameras and two targeting microphones, and validates them on real robotic systems. Through large-scale evaluations across various VLA architectures and tasks under varying attack parameters, we demonstrate significant vulnerabilities, with susceptibility patterns that reveal critical dependencies on task types and model designs. We further develop an adversarial-training-based defense that enhances VLA robustness against out-of-distribution physical perturbations caused by sensor attacks while preserving model performance. Our findings expose an urgent need for standardized robustness benchmarks and mitigation strategies to secure VLA deployments in safety-critical environments.
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。
