mlsanityData to 7 Oct 2026

TPC: Transformation-Specific Smoothing for Point Cloud Models

arXiv 2201.12733 ↗First posted 30 Jan 2022cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Point cloud models with neural network architectures have achieved great success and have been widely used in safety-critical applications, such as Lidar-based recognition systems in autonomous vehicles. However, such models are shown vulnerable to adversarial attacks which aim to apply stealthy semantic transformations such as rotation and tapering to mislead model predictions. In this paper, we propose a transformation-specific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks. We first categorize common 3D transformations into three categories: additive (e.g., shearing), composable (e.g., rotation), and indirectly composable (e.g., tapering), and we present generic robustness certification strategies for all categories respectively. We then specify unique certification protocols for a range of specific semantic transformations and their compositions. Extensive experiments on several common 3D transformations show that TPC significantly outperforms the state of the art. For example, our framework boosts the certified accuracy against twisting transformation along z-axis (within 20^circ) from 20.3% to 83.8%. Codes and models are available at https://github.com/chuwd19/Point-Cloud-Smoothing.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 30 Jan 2022.

Builds on

36 of 50 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  9. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  10. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  11. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  12. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
24 more
  1. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  2. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  3. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  4. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  5. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  6. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  7. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  8. 2018Generating 3D Adversarial Point Cloudscited by 144
  9. 2018Scaling provable adversarial defensescited by 141
  10. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
  11. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  12. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  13. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  14. 2019SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editingcited by 93
  15. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  16. 20163D Fully Convolutional Network for Vehicle Detection in Point Cloudcited by 57
  17. 2020Certified Defense to Image Transformations via Randomized Smoothingcited by 51
  18. 2020TSS: Transformation-Specific Smoothing for Robustness Certificationcited by 49
  19. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  20. 2018Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentationcited by 40
  21. 2021Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neuronscited by 40
  22. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  23. 2021Robustness Certification for Point Cloud Modelscited by 16
  24. 2021Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimationcited by 8

Built on by

Cited by year

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

10 papers.

  1. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  2. 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Needcited by 16
  3. 2022Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivitycited by 15
  4. 2023Hierarchical Randomized Smoothingcited by 9
  5. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  6. 2022Robustness Certification of Visual Perception Models via Camera Motion Smoothingcited by 3
  7. 2023Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbationscited by 2
  8. 2024COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attackscited by 2
  9. 2025Generating Adversarial Point Clouds Using Diffusion Modelcited by 1
  10. 2023Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approachcited by 0