mlsanityData to 7 Oct 2026

On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks

arXiv 2002.12222 ↗First posted 27 Feb 2020cs.LG stat.MLcited by 46

Not on the map. Why?

Abstract (arXiv)

While deep learning in 3D domain has achieved revolutionary performance in many tasks, the robustness of these models has not been sufficiently studied or explored. Regarding the 3D adversarial samples, most existing works focus on manipulation of local points, which may fail to invoke the global geometry properties, like robustness under linear projection that preserves the Euclidean distance, i.e., isometry. In this work, we show that existing state-of-the-art deep 3D models are extremely vulnerable to isometry transformations. Armed with the Thompson Sampling, we develop a black-box attack with success rate over 95% on ModelNet40 data set. Incorporating with the Restricted Isometry Property, we propose a novel framework of white-box attack on top of spectral norm based perturbation. In contrast to previous works, our adversarial samples are experimentally shown to be strongly transferable. Evaluated on a sequence of prevailing 3D models, our white-box attack achieves success rates from 98.88% to 100%. It maintains a successful attack rate over 95% even within an imperceptible rotation range [± 2.81circ].

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 10; 2023: 10; 2024: 6; 2025: 5; 2026: 1.

46 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  3. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  4. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  5. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  6. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 34
  7. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  8. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  9. 2022Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attackscited by 19
  10. 2023Towards Viewpoint-Invariant Visual Recognition via Adversarial Trainingcited by 19
  11. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  12. 2024PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermarkcited by 19
34 more
  1. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  2. 2021Robustness Certification for Point Cloud Modelscited by 16
  3. 2022Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processingcited by 16
  4. 2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
  5. 2021Interpreting Representation Quality of DNNs for 3D Point Cloud Processingcited by 12
  6. 2022ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotationcited by 12
  7. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  8. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  9. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  10. 2021The art of defense: letting networks fool the attackercited by 6
  11. 2021Adversarial Attack by Limited Point Cloud Surface Modificationscited by 6
  12. 2023PointCert: Point Cloud Classification with Deterministic Certified Robustness Guaranteescited by 6
  13. 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6
  14. 20223DVerifier: Efficient Robustness Verification for 3D Point Cloud Modelscited by 5
  15. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  16. 2021Staying in Shape: Learning Invariant Shape Representations using Contrastive Learningcited by 4
  17. 2022Random Walks for Adversarial Meshescited by 3
  18. 2023Exorcising ''Wraith'': Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attackscited by 3
  19. 2021Generating Unrestricted 3D Adversarial Point Cloudscited by 2
  20. 2022A Simple Strategy to Provable Invariance via Orbit Mappingcited by 2
  21. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  22. 2024Robust 3D Point Clouds Classification based on Declarative Defenderscited by 2
  23. 2024Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shiftscited by 1
  24. 2025RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalizationcited by 1
  25. 2025Transferable and Undefendable Point Cloud Attacks via Medial Axis Transformcited by 1
  26. 2021Dynamics-aware Adversarial Attack of 3D Sparse Convolution Networkcited by 0
  27. 2023Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Realitycited by 0
  28. 2024Transferable 3D Adversarial Shape Completion using Diffusion Modelscited by 0
  29. 2024Hard-Label Black-Box Attacks on 3D Point Cloudscited by 0
  30. 2024Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Fieldcited by 0
  31. 2025Cage-Based Deformation for Transferable and Undefendable Point Cloud Attackcited by 0
  32. 2025AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fieldscited by 0
  33. 2025Multimodal Robust Prompt Distillation for 3D Point Cloud Modelscited by 0
  34. 2026Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspectivecited by 0