PointGuard: Provably Robust 3D Point Cloud Classification

03/04/2021
by   Hongbin Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/03/2023

PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees

Point cloud classification is an essential component in many security-cr...
research
10/03/2022

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

Multi-label classification, which predicts a set of labels for an input,...
research
11/23/2019

Visualizing Point Cloud Classifiers by Curvature Smoothing

Recently, several networks that operate directly on point clouds have be...
research
10/03/2021

A Robust Scheme for 3D Point Cloud Copy Detection

Most existing 3D geometry copy detection research focused on 3D watermar...
research
07/24/2020

On anisotropic diffusion equations for label propagation

In many problems in data classification one wishes to assign labels to p...
research
07/15/2022

3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models

3D point cloud models are widely applied in safety-critical scenes, whic...
research
08/10/2023

Critical Points ++: An Agile Point Cloud Importance Measure for Robust Classification, Adversarial Defense and Explainable AI

The ability to cope accurately and fast with Out-Of-Distribution (OOD) s...

Please sign up or login with your details

Forgot password? Click here to reset