论文标题
单眼预测的靶向对抗扰动
Targeted Adversarial Perturbations for Monocular Depth Prediction
论文作者
论文摘要
我们研究对抗扰动对单眼深度预测任务的影响。具体而言，我们探讨了小型，不可感知的加性扰动有选择地改变场景几何形状的能力。我们表明，这种扰动不仅可以在全球范围内重新缩放相机的预测距离，还可以改变预测以匹配其他目标场景。我们还表明，当给出语义或实例信息时，扰动可能会欺骗网络以改变场景中特定类别或实例的深度，甚至在保留场景的其余部分时将其删除。为了了解目标扰动的影响，我们对最新的单眼预测方法进行实验。我们的实验揭示了单眼深度预测网络中的脆弱性，并阐明了它们所学到的偏见和环境。
We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while preserving the rest of the scene. To understand the effect of targeted perturbations, we conduct experiments on state-of-the-art monocular depth prediction methods. Our experiments reveal vulnerabilities in monocular depth prediction networks, and shed light on the biases and context learned by them.
