Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90\% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.

翻译：智能机器人依赖目标检测模型来感知环境。随着深度学习安全领域的进展，已有研究表明目标检测模型易受对抗攻击影响。然而，先前研究主要集中于攻击静态图像或离线视频。因此，此类攻击能否危及动态环境中真实机器人应用的安全性仍不明确。本文通过首次提出针对目标检测模型的实时在线攻击，填补了这一空白。我们设计了三种攻击方法，能在指定位置制造不存在物体的边界框。这些攻击在约20次迭代内即可达到约90%的成功率。演示视频见https://youtu.be/zJZ1aNlXsMU。