面对操控威胁:评估端到端视觉语言动作模型的物理脆弱性
Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models
AI总结:
本文提出物理脆弱性评估流程PVEP,系统评估端到端视觉语言动作模型在分布外样本、排版视觉提示和对抗补丁攻击三类物理威胁下的鲁棒性,并分析其性能波动规律。
摘要:
近年来,在多模态大语言模型(MLLMs)发展的推动下,视觉语言动作模型(VLAMs)被提出,以在机器人操控任务的开放词汇场景中取得更好性能。由于操控任务涉及与物理世界的直接交互,在执行该任务过程中确保鲁棒性和安全性始终是一个非常关键的问题。本文通过综合当前关于MLLMs的安全研究以及操控任务在物理世界中的具体应用场景,全面评估VLAMs在面对潜在物理威胁时的表现。具体而言,我们提出了物理脆弱性评估流程(PVEP),该流程能够尽可能纳入多种视觉模态的物理威胁,用于评估VLAMs的物理鲁棒性。PVEP中的物理威胁具体包括分布外样本、基于排版的视觉提示以及对抗性补丁攻击。通过比较VLAMs在受到攻击前后的性能波动,我们提供了关于VLAMs如何应对不同物理威胁的可推广的分析。
英文摘要:
Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since manipulation tasks involve direct interaction with the physical world, ensuring robustness and safety during the execution of this task is always a very critical issue. In this paper, by synthesizing current safety research on MLLMs and the specific application scenarios of the manipulation task in the physical world, we comprehensively evaluate VLAMs in the face of potential physical threats. Specifically, we propose the Physical Vulnerability Evaluating Pipeline (PVEP) that can incorporate as many visual modal physical threats as possible for evaluating the physical robustness of VLAMs. The physical threats in PVEP specifically include Out-of-Distribution, Typography-based Visual Prompt, and Adversarial Patch Attacks. By comparing the performance fluctuations of VLAMs before and after being attacked, we provide generalizable \textbf{\textit{Analyses}} of how VLAMs respond to different physical threats.
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。