研究人员开发了VLA-Hijack，一个新颖的对抗性框架，旨在利用视觉-语言-动作（VLA）模型的漏洞。该方法通过创建“幻影具身”，利用机器人手臂的视觉自我定位能力来破坏其运动规划能力。VLA-Hijack在白盒场景中表现出更高的效率，并在黑盒设置中跨不同模型架构和领域展现出更优越的可迁移性。 AI
影响 这项研究揭示了VLA模型的一个关键漏洞，可能影响其在现实世界机器人应用中的安全部署。
排序理由 该集群包含一篇详细介绍针对AI模型的新型对抗性攻击方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.28083v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models have emerged as powerful generalist policies, their severe vulnerability to adversarial patches significantly hinders their deployment in safety-critical domains. Moreover, existing patch at…
While Vision-Language-Action (VLA) models have emerged as powerful generalist policies, their severe vulnerability to adversarial patches significantly hinders their deployment in safety-critical domains. Moreover, existing patch attacks primarily focus on white-box settings, hea…