Robustness Certification for Point Cloud Models

03/30/2021
by   Tobias Lorenz, et al.
0

The use of deep 3D point cloud models in safety-critical applications, such as autonomous driving, dictates the need to certify the robustness of these models to semantic transformations. This is technically challenging as it requires a scalable verifier tailored to point cloud models that handles a wide range of semantic 3D transformations. In this work, we address this challenge and introduce 3DCertify, the first verifier able to certify robustness of point cloud models. 3DCertify is based on two key insights: (i) a generic relaxation based on first-order Taylor approximations, applicable to any differentiable transformation, and (ii) a precise relaxation for global feature pooling, which is more complex than pointwise activations (e.g., ReLU or sigmoid) but commonly employed in point cloud models. We demonstrate the effectiveness of 3DCertify by performing an extensive evaluation on a wide range of 3D transformations (e.g., rotation, twisting) for both classification and part segmentation tasks. For example, we can certify robustness against rotations by ±60^∘ for 95.7 up to 15.6

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2022

TPC: Transformation-Specific Smoothing for Point Cloud Models

Point cloud models with neural network architectures have achieved great...
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
11/24/2020

On the Adversarial Robustness of 3D Point Cloud Classification

3D point clouds play pivotal roles in various safety-critical fields, su...
research
12/11/2021

Attacking Point Cloud Segmentation with Color-only Perturbation

Recent research efforts on 3D point-cloud semantic segmentation have ach...
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
09/19/2020

Efficient Certification of Spatial Robustness

Recent work has exposed the vulnerability of computer vision models to s...
research
06/14/2018

Action Learning for 3D Point Cloud Based Organ Segmentation

We propose a novel point cloud based 3D organ segmentation pipeline util...

Please sign up or login with your details

Forgot password? Click here to reset