Intelligent robots hinge on accurate object detection models to perceive the environment. Advances in deep learning security unveil that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. It is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. There is still a gap between theoretical discoveries and real-world applications. We bridge the gap by proposing the first real-time online attack against object detection models. We devised three attacks that fabricate bounding boxes for nonexistent objects at desired locations.
翻译:智能机器人依靠精确的物体探测模型来观测环境。深层学习安全显示,物体探测模型很容易受到对抗性攻击。然而,先前的研究主要侧重于攻击静态图像或离线视频。这种攻击是否会危及动态环境中的实世机器人应用尚不清楚。理论发现与真实世界应用之间仍有差距。我们通过提出首次实时对物体探测模型进行在线攻击来弥合差距。我们设计了三次攻击,为理想地点不存在的物体制造了捆绑箱。