mlsanityData to 14 Oct 2026

PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition

arXiv 2208.09801 ↗First posted 21 Aug 2022cs.CV cs.CR cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in the physical world, deep learning is notorious for its vulnerability to adversarial attacks. In this work, we first identify that the state-of-the-art empirical defense, adversarial training, has a major limitation in applying to 3D point cloud models due to gradient obfuscation. We further propose PointDP, a purification strategy that leverages diffusion models to defend against 3D adversarial attacks. We extensively evaluate PointDP on six representative 3D point cloud architectures, and leverage 10+ strong and adaptive attacks to demonstrate its lower-bound robustness. Our evaluation shows that PointDP achieves significantly better robustness than state-of-the-art purification methods under strong attacks. Results of certified defenses on randomized smoothing combined with PointDP will be included in the near future.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 69 of its 85 references that are in the map. First posted on arXiv 21 Aug 2022.

Builds on

69 of 85 references.

References · 69

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  12. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
38 more
  1. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  2. 2020Point Transformercited by 1,470
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  5. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  9. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  13. 2020PCT: Point cloud transformercited by 732
  14. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  15. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  16. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  17. 2019Adversarial Training for Free!cited by 643
  18. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  19. 2022Diffusion Models for Adversarial Purificationcited by 476
  20. 2019On Evaluating Adversarial Robustnesscited by 447
  21. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  22. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  23. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  24. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  25. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  26. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  27. 2017Submanifold Sparse Convolutional Networkscited by 223
  28. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  29. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  30. 2018Spatially Transformed Adversarial Examplescited by 195
  31. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  32. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  33. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  34. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
  35. 2018Generating 3D Adversarial Point Cloudscited by 144
  36. 2022(Certified!!) Adversarial Robustness for Free!cited by 132
  37. 2018PointCloud Saliency Mapscited by 112
  38. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 7; 2024: 1; 2025: 1; 2026: 2.

16 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purificationcited by 36
  3. 2022DensePure: Understanding Diffusion Models towards Adversarial Robustnesscited by 33
  4. 2023CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perceptioncited by 14
  5. 2023VPA: Fully Test-Time Visual Prompt Adaptationcited by 11
  6. 2022Improving Adversarial Robustness by Contrastive Guided Diffusion Processcited by 8
  7. 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusioncited by 8
  8. 2023Diffusion models meet image counter-forensicscited by 6
  9. 2024Towards Robust 3D Pose Transfer with Adversarial Learningcited by 4
  10. 2023A Diffusion Model for Event Skeleton Generationcited by 3
  11. 2023On-ramp and Off-ramp Traffic Flows Estimation Based on A Data-driven Transfer Learning Frameworkcited by 3
  12. 2023Asymmetric Diffusion Based Channel-Adaptive Secure Wireless Semantic Communicationscited by 2
4 more
  1. 2022Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classificationcited by 1
  2. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  3. 2026PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Waveletscited by 0
  4. 2026Generative AI and Federated Learning for Intrusion Detection Systems: A Surveycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generating Adversarial Point Clouds Using Diffusion Model
  2. 2024Transferable 3D Adversarial Shape Completion using Diffusion Models
  3. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloud
  4. 2025Multimodal Robust Prompt Distillation for 3D Point Cloud Models
  5. 2023Self-supervised adversarial masking for 3D point cloud representation learning
  6. 2021A Backdoor Attack against 3D Point Cloud Classifiers
  7. 2024iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
  8. 2024Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features