(2021) Robustness Certification for Point Cloud Models.
|
Text
lorenz2021robustness.pdf - Accepted Version Download (453kB) | Preview |
Abstract
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 real-world 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 the 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% of point clouds, and our max pool relaxation increases certification by up to 15.6%.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Mario Fritz (MF) |
| Conference: | ICCV IEEE International Conference on Computer Vision |
| Depositing User: | Tobias Lorenz |
| Date Deposited: | 13 Aug 2021 09:05 |
| Last Modified: | 15 Jun 2022 13:48 |
| Primary Research Area: | NRA2: Reliable Security Guarantees |
| URI: | https://publications.cispa.saarland/id/eprint/3467 |
Actions
Actions (login required)
 |
View Item |