Object detection is a crucial task in autonomous driving. While existing research has proposed various attacks on object detection, such as those using adversarial patches or stickers, the exploration of projection attacks on 3D surfaces remains largely unexplored. Compared to adversarial patches or stickers, which have fixed adversarial patterns, projection attacks allow for transient modifications to these patterns, enabling a more flexible attack. In this paper, we introduce an adversarial 3D projection attack specifically targeting object detection in autonomous driving scenarios. We frame the attack formulation as an optimization problem, utilizing a combination of color mapping and geometric transformation models. Our results demonstrate the effectiveness of the proposed attack in deceiving YOLOv3 and Mask R-CNN in physical settings. Evaluations conducted in an indoor environment show an attack success rate of up to 100% under low ambient light conditions, highlighting the potential damage of our attack in real-world driving scenarios.

翻译：目标检测是自动驾驶中的关键任务。尽管现有研究已提出多种针对目标检测的攻击方法，例如使用对抗性补丁或贴纸，但对三维表面投影攻击的探索仍基本处于空白。与具有固定对抗模式的对抗性补丁或贴纸相比，投影攻击允许对这些模式进行瞬态修改，从而实现更灵活的攻击。本文提出了一种专门针对自动驾驶场景中目标检测的对抗性三维投影攻击。我们将攻击建模为一个优化问题，结合了色彩映射与几何变换模型。实验结果表明，所提出的攻击在物理环境下能有效欺骗YOLOv3和Mask R-CNN。在室内环境中的评估显示，在低环境光条件下攻击成功率高达100%，这凸显了我们的攻击在现实驾驶场景中的潜在危害。