mlsanityData to 13 Oct 2026

Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack

arXiv 2507.00690 ↗First posted 1 Jul 2025cs.CV cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks on point clouds often impose strict geometric constraints to preserve plausibility; however, such constraints inherently limit transferability and undefendability. While deformation offers an alternative, existing unstructured approaches may introduce unnatural distortions, making adversarial point clouds conspicuous and undermining their plausibility. In this paper, we propose CageAttack, a cage-based deformation framework that produces natural adversarial point clouds. It first constructs a cage around the target object, providing a structured basis for smooth, natural-looking deformation. Perturbations are then applied to the cage vertices, which seamlessly propagate to the point cloud, ensuring that the resulting deformations remain intrinsic to the object and preserve plausibility. Extensive experiments on seven 3D deep neural network classifiers across three datasets show that CageAttack achieves a superior balance among transferability, undefendability, and plausibility, outperforming state-of-the-art methods. Codes will be made public upon acceptance.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 40 of its 68 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

40 of 68 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,992
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  8. 2020Point Transformercited by 1,465
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,203
  10. 2020PCT: Point cloud transformercited by 731
  11. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 584
28 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  2. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  3. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 385
  4. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  5. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  6. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 278
  7. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  8. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  9. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  10. 2018Generating 3D Adversarial Point Cloudscited by 144
  11. 2018PointCloud Saliency Mapscited by 112
  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. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  15. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 64
  16. 2019Adversarial Attack and Defense on Point Setscited by 63
  17. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  18. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  19. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  20. 2022Shape-invariant 3D Adversarial Point Cloudscited by 49
  21. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  22. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  23. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  24. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  25. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  26. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  27. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  28. 2020ShapeAdv: Generating Shape-Aware Adversarial 3D Point Cloudscited by 20

Built on by

Not cited yet.