当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
PointGuard: Provably Robust 3D Point Cloud Classification
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2021-03-04 , DOI: arxiv-2103.03046
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

3D point cloud classification has many safety-critical applications such as autonomous driving and robotic grasping. However, several studies showed that it is vulnerable to adversarial attacks. In particular, an attacker can make a classifier predict an incorrect label for a 3D point cloud via carefully modifying, adding, and/or deleting a small number of its points. Randomized smoothing is state-of-the-art technique to build certifiably robust 2D image classifiers. However, when applied to 3D point cloud classification, randomized smoothing can only certify robustness against adversarially {modified} points. In this work, we propose PointGuard, the first defense that has provable robustness guarantees against adversarially modified, added, and/or deleted points. Specifically, given a 3D point cloud and an arbitrary point cloud classifier, our PointGuard first creates multiple subsampled point clouds, each of which contains a random subset of the points in the original point cloud; then our PointGuard predicts the label of the original point cloud as the majority vote among the labels of the subsampled point clouds predicted by the point cloud classifier. Our first major theoretical contribution is that we show PointGuard provably predicts the same label for a 3D point cloud when the number of adversarially modified, added, and/or deleted points is bounded. Our second major theoretical contribution is that we prove the tightness of our derived bound when no assumptions on the point cloud classifier are made. Moreover, we design an efficient algorithm to compute our certified robustness guarantees. We also empirically evaluate PointGuard on ModelNet40 and ScanNet benchmark datasets.

中文翻译:

PointGuard:可靠的3D点云分类

3D点云分类具有许多安全关键型应用程序,例如自动驾驶和机器人抓取。但是,一些研究表明,它容易受到对抗性攻击。特别是,攻击者可以通过仔细修改,添加和/或删除少量点来使分类器为3D点云预测不正确的标签。随机平滑是建立可验证的强大2D图像分类器的最新技术。但是,当应用于3D点云分类时,随机平滑只能证明针对对抗{修改}点的鲁棒性。在这项工作中,我们提出了PointGuard,这是第一个具有可证明的鲁棒性保证的防御,可以防御对抗性修改,添加和/或删除的点。具体来说,给定3D点云和任意点云分类器,我们的PointGuard首先创建多个子采样点云,每个子云都包含原始点云中点的随机子集;然后我们的PointGuard会将原始点云的标签预测为由点云分类器预测的二次采样点云的标签中的多数票。我们的第一个主要的理论贡献是,当对抗性修改,添加和/或删除的点数有界时,我们证明PointGuard可预测3D点云的相同标签。我们的第二个主要理论贡献是,当不对点云分类器进行任何假设时,我们证明了导出边界的紧密性。此外,我们设计了一种有效的算法来计算我们的认证鲁棒性保证。我们还根据经验评估了ModelNet40和ScanNet基准数据集上的PointGuard。
更新日期:2021-03-05
down
wechat
bug