Typographic attacks trick household robots into physical manipulation errors

Researchers have demonstrated a new vulnerability in household robots that use vision-language models for object recognition. By placing specially designed stickers with text, attackers can trick the robots into misidentifying objects and performing incorrect actions, such as grasping the wrong item. This "typographic attack" exploits the shared embedding space of models like CLIP, leading to physical manipulation errors that were previously unexamined in full robot pipelines. AI

影响 Highlights a novel security threat to embodied AI agents, potentially impacting the safety and reliability of future household robots.

排序理由 Academic paper detailing a new type of security vulnerability in AI systems. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Habitat
• HomeRobot benchmark

• 安全
• 论文
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →