mlsanityData to 7 Oct 2026

Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing

arXiv 2207.13326 ↗First posted 27 Jul 2022cs.CV eess.IVcited by 16

Not on the map. Why?

Abstract (arXiv)

With the increasing attention in various 3D safety-critical applications, point cloud learning models have been shown to be vulnerable to adversarial attacks. Although existing 3D attack methods achieve high success rates, they delve into the data space with point-wise perturbation, which may neglect the geometric characteristics. Instead, we propose point cloud attacks from a new perspective -- the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that corresponds to varying certain geometric structure. Specifically, leveraging on graph signal processing, we first adaptively transform the coordinates of points onto the spectral domain via graph Fourier transform (GFT) for compact representation. Then, we analyze the influence of different spectral bands on the geometric structure, based on which we propose to perturb the GFT coefficients via a learnable graph spectral filter. Considering the low-frequency components mainly contribute to the rough shape of the 3D object, we further introduce a low-frequency constraint to limit perturbations within imperceptible high-frequency components. Finally, the adversarial point cloud is generated by transforming the perturbed spectral representation back to the data domain via the inverse GFT. Experimental results demonstrate the effectiveness of the proposed attack in terms of both the imperceptibility and attack success rates.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 62 of its 95 references that are in the map. First posted on arXiv 27 Jul 2022.

Builds on

62 of 95 references.

References · 62

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2020Point Transformercited by 1,462
  10. 2017Deep Setscited by 1,394
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
38 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  2. 2016Adversarial Machine Learning at Scalecited by 934
  3. 2016Universal adversarial perturbationscited by 774
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  9. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  10. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  11. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  12. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  13. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  14. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  15. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  16. 2018Generating 3D Adversarial Point Cloudscited by 144
  17. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  18. 2018PointCloud Saliency Mapscited by 112
  19. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  20. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  21. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  22. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  23. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  24. 20203D Deep Learning on Medical Images: A Reviewcited by 76
  25. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  26. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  27. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  28. 2019Adversarial Attack and Defense on Point Setscited by 63
  29. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  30. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  31. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  32. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  33. 2022Shape-invariant 3D Adversarial Point Cloudscited by 49
  34. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  35. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  36. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  37. 2017Fast Resampling of 3D Point Clouds via Graphscited by 25
  38. 2020Graph Signal Processing for Geometric Data and Beyond: Theory and Applicationscited by 23

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 5; 2025: 4; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  2. 2023Density-Insensitive Unsupervised Domain Adaption on 3D Object Detectioncited by 31
  3. 2023A Survey on Spectral Graph Neural Networkscited by 26
  4. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  5. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  6. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  7. 2024Joint Top-Down and Bottom-Up Frameworks for 3D Visual Groundingcited by 3
  8. 2025Boosting Adversarial Transferability with Spatial Adversarial Alignmentcited by 1
  9. 20253D Test-time Adaptation via Graph Spectral Driven Point Shiftcited by 1
  10. 2026STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understandingcited by 1
  11. 2024Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Methodcited by 0
  12. 2024A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networkscited by 0
4 more
  1. 2024Hard-Label Black-Box Attacks on 3D Point Cloudscited by 0
  2. 2025First-place Solution for Streetscape Shop Sign Recognition Competitioncited by 0
  3. 2025Rethinking Gradient-based Adversarial Attacks on Point Cloud Classificationcited by 0
  4. 2026Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domaincited by 0