Abstract
In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been thoroughly examined. In this study, we conduct the first comprehensive investigation of the robustness of leading camera-based 3D object detection methods under various adversarial conditions. Our experiments reveal five interesting findings: (a) the use of accurate depth estimation effectively improves robustness; (b) depth-estimation-free approaches do not show superior robustness; (c) bird's-eye-view-based representations exhibit greater robustness against localization attacks; (d) incorporating multi-frame benign inputs can effectively mitigate adversarial attacks; and (e) addressing long-tail problems can enhance robustness. We hope our work can provide guidance for the design of future camera-based object detection modules with improved adversarial robustness.
Abstract (translated)
近年来,基于相机的三维物体检测以其在低计算成本下实现高性能而获得了广泛关注。然而,这些方法对对抗攻击的鲁棒性并没有得到充分的研究。在本研究中,我们对几种主要的基于相机的三维物体检测方法在不同对抗条件下的鲁棒性进行了全面的调查。我们的实验发现了五个有趣的结论:(a) 使用准确的深度估计可以有效地提高鲁棒性;(b) 深度估计无的方法并没有表现出更好的鲁棒性;(c) 基于视野表示的方法在抵御定位攻击方面表现出更强的鲁棒性;(d) 包含多帧良性输入可以有效地减轻对抗攻击;(e) 解决长尾问题可以增强鲁棒性。我们希望我们的工作可以为未来改进对抗鲁棒性的相机based物体检测模块的设计提供指导。
URL
https://arxiv.org/abs/2301.10766
