TL;DR本文针对深度神经网络生成对抗样本的问题展开了研究,提出了针对 3D 物理性质改变的对抗样本生成方法,并通过在 2D 输入图像前增加可渲染模块的方式,成功地将对抗扰动提升到物理空间,检验了所设计的方法的有效性。
Abstract
Generating adversarial examples is an intriguing problem and an important way
of understanding the working mechanism of deep neural networks. Most existing
approaches generated perturbations in the image space, i