论文标题
如果防御：通过基于隐式功能的恢复，3D对抗点云防线
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
论文作者
论文摘要
点云是在许多基本应用中广泛使用的重要3D数据表示。利用深层神经网络，最近的作品在处理3D点云方面取得了巨大的成功。但是，这些深层神经网络容易受到各种3D对抗攻击的攻击，这些攻击可以总结为两种主要类型：影响局部点分布的点扰动，以及导致几何形状变化的表面变形。在本文中，我们通过学习恢复受攻击的云层的清洁点云，同时解决上述攻击。更具体地说，我们提出了一个if-defense框架，以直接优化具有几何学和分布感知约束的输入点的坐标。前者的目标是通过隐式函数恢复点云的表面，而后者则鼓励分布均匀的点。我们的实验结果表明，如果防御能够针对对PointNet，PointNet ++，DGCNN，PointConv和RS-CNN的现有3D对抗攻击的最新防御性能。例如，与以前的方法相比，如果防御能力提高了分类准确性的20.02％，则针对显着点的降低攻击，而对LG-GAN对PointNet的攻击则提高了16.29％。我们的代码可从https://github.com/wuziyi616/if-defense获得。
Point cloud is an important 3D data representation widely used in many essential applications. Leveraging deep neural networks, recent works have shown great success in processing 3D point clouds. However, those deep neural networks are vulnerable to various 3D adversarial attacks, which can be summarized as two primary types: point perturbation that affects local point distribution, and surface distortion that causes dramatic changes in geometry. In this paper, we simultaneously address both the aforementioned attacks by learning to restore the clean point clouds from the attacked ones. More specifically, we propose an IF-Defense framework to directly optimize the coordinates of input points with geometry-aware and distribution-aware constraints. The former aims to recover the surface of point cloud through implicit function, while the latter encourages evenly-distributed points. Our experimental results show that IF-Defense achieves the state-of-the-art defense performance against existing 3D adversarial attacks on PointNet, PointNet++, DGCNN, PointConv and RS-CNN. For example, compared with previous methods, IF-Defense presents 20.02% improvement in classification accuracy against salient point dropping attack and 16.29% against LG-GAN attack on PointNet. Our code is available at https://github.com/Wuziyi616/IF-Defense.
