arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07104cs.CVcs.AI
收藏

扩展到现实:3D环境中的提示注入

Extended to Reality: Prompt Injection in 3D Environments

Zhuoheng Li, Ying Chen

AI总结:

研究提出PI3D攻击,通过在3D环境中放置带文本的物理物体来注入提示,挑战多模态大语言模型的安全性。

摘要:

多模态大语言模型(MLLMs)在3D环境中解释和执行视觉输入的能力得到了提升,使机器人和情境对话代理等应用成为可能。当MLLMs在摄像头捕获的物理世界视图上进行推理时,一个新的攻击面出现:攻击者可以放置带有文本的物理物体来覆盖MLLMs的预期任务。尽管先前的工作研究了文本领域和通过数字编辑的2D图像中的提示注入,但这些攻击在3D物理环境中的运作方式仍然不清楚。为了弥补这一差距,我们引入了PI3D,一种针对3D环境中MLLMs的提示注入攻击,通过放置带有文本的物理物体而不是数字图像编辑来实现。我们提出了并解决了识别带有注入文本的有效3D物体姿态(位置和方向)的问题,其中攻击者的目的是使MLLM执行注入的任务,同时确保物体放置在物理上是合理的。实验表明,PI3D在多种MLLMs下不同的摄像轨迹中是一种有效的攻击。我们进一步评估了现有防御措施,并显示它们不足以防御PI3D。

英文摘要:

Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over camera-captured views of the physical world, a new attack surface emerges: an attacker can place text-bearing physical objects in the environment to override MLLMs' intended task. While prior work has studied prompt injection in the text domain and through digitally edited 2D images, limited attention has been paid to how these attacks function in 3D environments. To bridge the gap, we introduce PI3D, a prompt injection attack against MLLMs in 3D environments, realized through text-bearing object placement rather than digital image edits. We formulate and solve the problem of identifying an effective pose (position and orientation) for a 3D object with injected text, where the attacker's goal is to induce the MLLM to perform the injected task while ensuring that the object placement remains physically plausible. Experiment results demonstrate that PI3D is an effective attack against multiple MLLMs under diverse camera trajectories. We further evaluate a range of defenses and show that they are not sufficient to reliably defend against PI3D.

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。

↑