In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel \underline{S}tealthy \underline{A}dversarial \underline{A}ttacks on \underline{M}DE (SAAM) that compromises MDE by either corrupting the estimated distance or causing an object to seamlessly blend into its surroundings. Our experiments, demonstrate that the designed stealthy patch successfully causes a DNN-based MDE to misestimate the depth of objects. In fact, our proposed adversarial patch achieves a significant 60\% depth error with 99\% ratio of the affected region. Importantly, despite its adversarial nature, the patch maintains a naturalistic appearance, making it inconspicuous to human observers. We believe that this work sheds light on the threat of adversarial attacks in the context of MDE on edge devices. We hope it raises awareness within the community about the potential real-life harm of such attacks and encourages further research into developing more robust and adaptive defense mechanisms.

翻译：本文研究了单目深度估计（MDE）对对抗性补丁的脆弱性。我们提出了一种新颖的针对MDE的隐秘对抗攻击（SAAM），该攻击通过破坏估计距离或使目标无缝融入周围环境来危及MDE系统。实验证明，我们设计的隐秘补丁能够成功使基于深度神经网络的MDE模型错误估计目标的深度。事实上，我们提出的对抗补丁在受影响区域占比99%的情况下实现了显著的60%深度误差。值得关注的是，尽管具有对抗性，该补丁仍能保持自然外观，使其对人类观察者不易察觉。我们相信，这项工作揭示了边缘设备上MDE系统面临对抗性攻击的威胁，希望引发学界对此类攻击潜在现实危害的重视，并推动更鲁棒自适应防御机制的研究。