mlsanityData to 7 Oct 2026

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

arXiv 2307.00309 ↗First posted 1 Jul 2023cs.CV cs.LG eess.IVcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 98 of its 175 references that are in the map. First posted on arXiv 1 Jul 2023.

Builds on

98 of 175 references.

References · 98

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  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. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
38 more
  1. 2016Adversarial examples in the physical worldcited by 1,762
  2. 2020Point Transformercited by 1,462
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  8. 2020Convolutional Occupancy Networkscited by 760
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  12. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  13. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  14. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  15. 2017Adversarial Patchcited by 514
  16. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  17. 2018Spherical CNNscited by 452
  18. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  19. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  20. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  21. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  22. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  23. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  24. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  25. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  26. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  27. 2018Spatially Transformed Adversarial Examplescited by 195
  28. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  29. 2019Self-Driving Cars: A Surveycited by 147
  30. 2018Generating 3D Adversarial Point Cloudscited by 144
  31. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  32. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  33. 2017A Review on Deep Learning Techniques Applied to Semantic Segmentationcited by 122
  34. 2018PointCloud Saliency Mapscited by 112
  35. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  36. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  37. 2018SparseFool: a few pixels make a big differencecited by 94
  38. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2024Attack on Scene Flow using Point Cloudscited by 1
  2. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  3. 2025Hi-ALPS -- An Experimental Robustness Quantification of Six LiDAR-based Object Detection Systems for Autonomous Drivingcited by 0
  4. 2025KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Searchcited by 0
  5. 20263D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanismcited by 0