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感知环境。随着深度学习安全领域的进展，研究表明目标检测模型易受对抗性攻击。然而，现有研究主要集中于攻击静态图像或离线视频，因此尚不清楚此类攻击能否威胁动态环境中的实际机器人应用。本文通过提出首个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，可在指定位置为不存在物体伪造边界框，该攻击在约20次迭代内达到约90%的成功率。演示视频见https://youtu.be/zJZ1aNlXsMU。