TPC: Transformation-Specific Smoothing for Point Cloud Models

01/30/2022
by   Wenda Chu, et al.
5

Point cloud models with neural network architectures have achieved great success and have been widely used in safety-critical applications, such as Lidar-based recognition systems in autonomous vehicles. However, such models are shown vulnerable against adversarial attacks which aim to apply stealthy semantic transformations such as rotation and tapering to mislead model predictions. In this paper, we propose a transformation-specific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks. We first categorize common 3D transformations into three categories: additive (e.g., shearing), composable (e.g., rotation), and indirectly composable (e.g., tapering), and we present generic robustness certification strategies for all categories respectively. We then specify unique certification protocols for a range of specific semantic transformations and their compositions. Extensive experiments on several common 3D transformations show that TPC significantly outperforms the state of the art. For example, our framework boosts the certified accuracy against twisting transformation along z-axis (within 20^∘) from 20.3% to 83.8%.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/30/2021

Robustness Certification for Point Cloud Models

The use of deep 3D point cloud models in safety-critical applications, s...
research
08/17/2022

Imperceptible and Robust Backdoor Attack in 3D Point Cloud

With the thriving of deep learning in processing point cloud data, recen...
research
02/27/2020

Provable Robust Learning Based on Transformation-Specific Smoothing

As machine learning systems become pervasive, safeguarding their securit...
research
09/19/2020

Efficient Certification of Spatial Robustness

Recent work has exposed the vulnerability of computer vision models to s...
research
06/09/2022

GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing

Certified defenses such as randomized smoothing have shown promise towar...
research
11/20/2019

Utility Analysis of Network Architectures for 3D Point Cloud Processing

In this paper, we diagnose deep neural networks for 3D point cloud proce...
research
03/08/2022

ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation

Point cloud classifiers with rotation robustness have been widely discus...

Please sign up or login with your details

Forgot password? Click here to reset