mlsanityData to 7 Oct 2026

3D Adversarial Attacks Beyond Point Cloud

arXiv 2104.12146 ↗First posted 25 Apr 2021cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these attacks in the physical scenario, a generated adversarial 3D point cloud need to be reconstructed to mesh, which leads to a significant drop in its adversarial effect. In this paper, we propose a strong 3D adversarial attack named Mesh Attack to address this problem by directly performing perturbation on mesh of a 3D object. In order to take advantage of the most effective gradient-based attack, a differentiable sample module that back-propagate the gradient of point cloud to mesh is introduced. To further ensure the adversarial mesh examples without outlier and 3D printable, three mesh losses are adopted. Extensive experiments demonstrate that the proposed scheme outperforms SOTA 3D attacks by a significant margin. We also achieved SOTA performance under various defenses. Our code is available at: https://github.com/cuge1995/Mesh-Attack.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 25 Apr 2021.

Builds on

39 of 61 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2016Adversarial Machine Learning at Scalecited by 934
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
27 more
  1. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  2. 2016Universal adversarial perturbationscited by 774
  3. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  6. 2017One pixel attack for fooling deep neural networkscited by 579
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2017Adversarial Patchcited by 514
  9. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  10. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  13. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  14. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  15. 2018Generating 3D Adversarial Point Cloudscited by 144
  16. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  17. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  18. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  19. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  20. 2018PointCloud Saliency Mapscited by 112
  21. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  22. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  23. 2021BRepNet: A topological message passing system for solid modelscited by 92
  24. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  25. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  26. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  27. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 3; 2024: 7; 2025: 9; 2026: 1.

26 papers.

Sort:

  1. 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognitioncited by 33
  2. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  3. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  4. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  5. 2022Boosting 3D Adversarial Attacks with Attacking On Frequencycited by 18
  6. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  7. 2024Toward Availability Attacks in 3D Point Cloudscited by 7
  8. 2022Improving transferability of 3D adversarial attacks with scale and shear transformationscited by 5
  9. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  10. 2024Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attackscited by 5
  11. 2024Towards Robust 3D Pose Transfer with Adversarial Learningcited by 4
  12. 2022Random Walks for Adversarial Meshescited by 3
14 more
  1. 2025NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundarycited by 2
  2. 2022Adversarial samples for deep monocular 6D object pose estimationcited by 1
  3. 2024Eidos: Efficient, Imperceptible Adversarial 3D Point Cloudscited by 1
  4. 20243D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Frameworkcited by 0
  5. 2024epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognitioncited by 0
  6. 2025Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attackscited by 0
  7. 2025Rethinking Gradient-based Adversarial Attacks on Point Cloud Classificationcited by 0
  8. 2025Cage-Based Deformation for Transferable and Undefendable Point Cloud Attackcited by 0
  9. 2025Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocolscited by 0
  10. 2025Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptionscited by 0
  11. 2025Skeleton-based Robust Registration Framework for Corrupted 3D Point Cloudscited by 0
  12. 2025AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fieldscited by 0
  13. 2025Multimodal Robust Prompt Distillation for 3D Point Cloud Modelscited by 0
  14. 2026Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Cloudscited by 0