mlsanityData to 14 Oct 2026

3DeformRS: Certifying Spatial Deformations on Point Clouds

arXiv 2204.05687 ↗First posted 12 Apr 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed practically and reliably. In this work, we propose 3DeformRS, a method to certify the robustness of point cloud Deep Neural Networks (DNNs) against real-world deformations. We developed 3DeformRS by building upon recent work that generalized Randomized Smoothing (RS) from pixel-intensity perturbations to vector-field deformations. In particular, we specialized RS to certify DNNs against parameterized deformations (e.g. rotation, twisting), while enjoying practical computational costs. We leverage the virtues of 3DeformRS to conduct a comprehensive empirical study on the certified robustness of four representative point cloud DNNs on two datasets and against seven different deformations. Compared to previous approaches for certifying point cloud DNNs, 3DeformRS is fast, scales well with point cloud size, and provides comparable-to-better certificates. For instance, when certifying a plain PointNet against a 3deg z-rotation on 1024-point clouds, 3DeformRS grants a certificate 3x larger and 20x faster than previous work.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

42 of 58 references.

References · 42

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  9. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  12. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
30 more
  1. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  2. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  3. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  5. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2017Countering Adversarial Images using Input Transformationscited by 520
  9. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  10. 2019On Evaluating Adversarial Robustnesscited by 447
  11. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  12. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 330
  13. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  14. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  15. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  16. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  17. 2018Generating 3D Adversarial Point Cloudscited by 144
  18. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  19. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  20. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  21. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  22. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  23. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  24. 2020DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshescited by 42
  25. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  26. 2020Data-Dependent Randomized Smoothingcited by 37
  27. 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
  28. 2021DeformRS: Certifying Input Deformations with Randomized Smoothingcited by 17
  29. 2021Robustness Certification for Point Cloud Modelscited by 16
  30. 2021Picasso: A CUDA-based Library for Deep Learning over 3D Meshescited by 4

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 1; 2025: 2.

10 papers.

  1. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 34
  2. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  3. 2023Improving Viewpoint Robustness for Visual Recognition via Adversarial Trainingcited by 7
  4. 2022Generalizability of Adversarial Robustness Under Distribution Shiftscited by 6
  5. 2023PointCert: Point Cloud Classification with Deterministic Certified Robustness Guaranteescited by 6
  6. 2022Certified Robustness in Federated Learningcited by 4
  7. 2022Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classificationcited by 1
  8. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  9. 2024Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Trainingcited by 0
  10. 2025Certified L2-Norm Robustness of 3D Point Cloud Recognition in the Frequency Domaincited by 0