Abstract
We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed posters, cause visual object tracking systems to become confused. For instance, as a target being tracked by a robot's camera moves in front of such a poster, our generated texture makes the tracker lock onto it and allows the target to evade. This work aims to fool seldom-targeted regression tasks, and in particular compares diverse optimization strategies: non-targeted, targeted, and a new family of guided adversarial losses. While we use the Expectation Over Transformation (EOT) algorithm to generate physical adversaries that fool tracking models when imaged under diverse conditions, we compare the impacts of different conditioning variables, including viewpoint, lighting, and appearances, to find practical attack setups with high resulting adversarial strength and convergence speed. We further showcase textures optimized solely using simulated scenes can confuse real-world tracking systems.
Abstract (translated)
我们提出了一种生成不显眼的纹理的系统,当它以数字或印刷海报的形式显示在物理世界中时,会导致视觉对象跟踪系统变得混乱。例如,当机器人摄像头跟踪的目标在海报前移动时,我们生成的纹理使跟踪器锁定在海报上,允许目标躲避。这项工作的目的是愚弄很少有针对性的回归任务,特别是比较不同的优化策略:无针对性的,有针对性的,以及一个新的被引导的对抗性损失家族。当我们使用期望过度转换(EOT)算法生成物理对手,在不同条件下成像时会愚弄跟踪模型,我们比较了不同条件变量的影响,包括视点、灯光和外观,以找到具有较高对抗力和协同作战能力的实际攻击设置。n收敛速度。我们进一步展示仅使用模拟场景优化的纹理,这可能会混淆真实的跟踪系统。
URL
https://arxiv.org/abs/1904.11042