CISPA
Browse
cispa_all_3467.pdf (443.23 kB)

Robustness Certification for Point Cloud Models

Download (443.23 kB)
conference contribution
posted on 2023-11-29, 18:17 authored by Tobias LorenzTobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev
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%.

History

Preferred Citation

Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh and Martin Vechev. Robustness Certification for Point Cloud Models. In: IEEE International Conference on Computer Vision (ICCV). 2021.

Primary Research Area

  • Reliable Security Guarantees

Secondary Research Area

  • Trustworthy Information Processing

Tertiary Research Area

  • Threat Detection and Defenses

Name of Conference

IEEE International Conference on Computer Vision (ICCV)

Legacy Posted Date

2021-08-13

Open Access Type

  • Gold

BibTeX

@inproceedings{cispa_all_3467, title = "Robustness Certification for Point Cloud Models", author = "Lorenz, Tobias and Ruoss, Anian and Balunović, Mislav and Singh, Gagandeep and Vechev, Martin", booktitle="{IEEE International Conference on Computer Vision (ICCV)}", year="2021", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC