mlsanityData to 7 Oct 2026

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

arXiv 2410.03644 ↗First posted 4 Oct 2024cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples; (ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, ie, even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at urlhttps://github.com/CGCL-codes/UnlearnablePC

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

45 of 62 references.

References · 45

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 2020PCT: Point cloud transformercited by 730
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  11. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
33 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  3. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  4. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  5. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  6. 2021Adversarial Examples Make Strong Poisonscited by 115
  7. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  8. 2019Adversarial Attack and Defense on Point Setscited by 63
  9. 2021A Backdoor Attack against 3D Point Cloud Classifierscited by 50
  10. 2020Precise Statistical Analysis of Classification Accuracies for Adversarial Trainingcited by 49
  11. 2022Transferable Unlearnable Examplescited by 41
  12. 2020The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalizationcited by 39
  13. 2022Unlearnable Clusters: Towards Label-agnostic Unlearnable Examplescited by 35
  14. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 34
  15. 2022Robust Unlearnable Examples: Protecting Data Against Adversarial Learningcited by 34
  16. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  17. 2024DarkSAM: Fooling Segment Anything Model to Segment Nothingcited by 32
  18. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  19. 2022One-Pixel Shortcut: on the Learning Preference of Deep Neural Networkscited by 29
  20. 2023CUDA: Convolution-based Unlearnable Datasetscited by 26
  21. 2022Imperceptible and Robust Backdoor Attack in 3D Point Cloudcited by 25
  22. 2023Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noisecited by 23
  23. 2022Self-Ensemble Protection: Training Checkpoints Are Good Data Protectorscited by 19
  24. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18
  25. 2024Game-Theoretic Unlearnable Example Generatorcited by 12
  26. 2019Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topologycited by 11
  27. 2022TPC: Transformation-Specific Smoothing for Point Cloud Modelscited by 10
  28. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9
  29. 2024Ungeneralizable Examplescited by 9
  30. 2024ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purificationcited by 9
  31. 2024Toward Availability Attacks in 3D Point Cloudscited by 7
  32. 2019Multi-Sensor 3D Object Box Refinement for Autonomous Drivingcited by 5
  33. 2021User configurable 3D object regeneration for spatial privacycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 8.

16 papers.

Sort:

By area:

  1. 2024PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentationcited by 14
  2. 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learningcited by 11
  3. 2025Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Trackingcited by 9
  4. 2025SegTrans: Transferable Adversarial Examples for Segmentation Modelscited by 8
  5. 2025A Survey on Unlearnable Datacited by 5
  6. 2025T2UE: Generating Unlearnable Examples from Text Descriptionscited by 3
  7. 2026Full spectrum Unlearnable Examples via Spectral Equalizationcited by 3
  8. 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Informationcited by 2
  9. 2026Transferable Physical-World Adversarial Patches Against Pedestrian Detection Modelscited by 2
  10. 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restorationcited by 1
  11. 2026Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Drivingcited by 1
  12. 2025Learning to Generate Cross-Task Unexploitable Examplescited by 0
4 more
  1. 2026UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embeddingcited by 0
  2. 2026VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasioncited by 0
  3. 2026ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalizationcited by 0
  4. 2026Semantic Privacy Protection with Utility Preservation for 3D Point Cloudscited by 0