mlsanityData to 7 Oct 2026

PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees

arXiv 2303.01959 ↗First posted 3 Mar 2023cs.CR cs.AI cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are vulnerable to adversarially perturbed point clouds. Existing certified defenses against adversarial point clouds suffer from a key limitation: their certified robustness guarantees are probabilistic, i.e., they produce an incorrect certified robustness guarantee with some probability. In this work, we propose a general framework, namely PointCert, that can transform an arbitrary point cloud classifier to be certifiably robust against adversarial point clouds with deterministic guarantees. PointCert certifiably predicts the same label for a point cloud when the number of arbitrarily added, deleted, and/or modified points is less than a threshold. Moreover, we propose multiple methods to optimize the certified robustness guarantees of PointCert in three application scenarios. We systematically evaluate PointCert on ModelNet and ScanObjectNN benchmark datasets. Our results show that PointCert substantially outperforms state-of-the-art certified defenses even though their robustness guarantees are probabilistic.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 41 of its 54 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

41 of 54 references.

References · 41

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2020Point Transformercited by 1,462
  6. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
  9. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  10. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  11. 2018PCN: Point Completion Networkcited by 382
  12. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
29 more
  1. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  2. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  3. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  4. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  5. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  6. 2018Generating 3D Adversarial Point Cloudscited by 144
  7. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  8. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  9. 2018PointCloud Saliency Mapscited by 112
  10. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  11. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  12. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  13. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  14. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  15. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  16. 2019Adversarial Attack and Defense on Point Setscited by 63
  17. 2017Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classificationcited by 56
  18. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  19. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  20. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  21. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  22. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  23. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  24. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  25. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  26. 2020Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbationscited by 16
  27. 2021Robustness Certification for Point Cloud Modelscited by 16
  28. 2021Interpreting Representation Quality of DNNs for 3D Point Cloud Processingcited by 12
  29. 20223DeformRS: Certifying Spatial Deformations on Point Cloudscited by 10

Built on by

Cited by year

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

6 papers.

  1. 2024Fast and Simple Explainability for Point Cloud Networkscited by 6
  2. 2024MMCert: Provable Defense against Adversarial Attacks to Multi-modal Modelscited by 4
  3. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  4. 2025Computation-Efficient and Recognition-Friendly 3D Point Cloud Privacy Protectioncited by 0
  5. 2025Rethinking Gradient-based Adversarial Attacks on Point Cloud Classificationcited by 0
  6. 2025Certified L2-Norm Robustness of 3D Point Cloud Recognition in the Frequency Domaincited by 0