mlsanityData to 7 Oct 2026

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

arXiv 2202.07261 ↗First posted 15 Feb 2022cs.CV eess.IVcited by 19

Not on the map. Why?

Abstract (arXiv)

With the maturity of depth sensors, point clouds have received increasing attention in various applications such as autonomous driving, robotics, surveillance, etc., while deep point cloud learning models have shown to be vulnerable to adversarial attacks. Existing attack methods generally add/delete points or perform point-wise perturbation over point clouds to generate adversarial examples in the data space, which may neglect the geometric characteristics of point clouds. Instead, we propose point cloud attacks from a new perspective -- Graph Spectral Domain Attack (GSDA), aiming to perturb transform coefficients in the graph spectral domain that corresponds to varying certain geometric structure. In particular, we naturally represent a point cloud over a graph, and adaptively transform the coordinates of points into the graph spectral domain via graph Fourier transform (GFT) for compact representation. We then analyze the influence of different spectral bands on the geometric structure of the point cloud, based on which we propose to perturb the GFT coefficients in a learnable manner guided by an energy constraint loss function. Finally, the adversarial point cloud is generated by transforming the perturbed spectral representation back to the data domain via the inverse GFT (IGFT). Experimental results demonstrate the effectiveness of the proposed GSDA in terms of both imperceptibility and attack success rates under a variety of defense strategies. The code is available at https://github.com/WoodwindHu/GSDA.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 46 of its 69 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

46 of 69 references.

References · 46

  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. 2017Deep Setscited by 1,394
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
34 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2016Universal adversarial perturbationscited by 774
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  5. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  6. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  7. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  8. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  9. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  10. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  11. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  12. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  13. 2018Generating 3D Adversarial Point Cloudscited by 144
  14. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  15. 2018PointCloud Saliency Mapscited by 112
  16. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  17. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  18. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  19. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  20. 20203D Deep Learning on Medical Images: A Reviewcited by 76
  21. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  22. 2019Adversarial Attack and Defense on Point Setscited by 63
  23. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  24. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  25. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  26. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  27. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  28. 2017Fast Resampling of 3D Point Clouds via Graphscited by 25
  29. 2020Graph Signal Processing for Geometric Data and Beyond: Theory and Applicationscited by 23
  30. 2019GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformationscited by 22
  31. 2019Spectral-GANs for High-Resolution 3D Point-cloud Generationcited by 17
  32. 2020Hypergraph Spectral Analysis and Processing in 3D Point Cloudcited by 14
  33. 2020Defense-PointNet: Protecting PointNet Against Adversarial Attackscited by 13
  34. 2019Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point Cloudscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 4; 2025: 4; 2026: 3.

19 papers.

Sort:

By area:

  1. 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognitioncited by 33
  2. 2023Density-Insensitive Unsupervised Domain Adaption on 3D Object Detectioncited by 31
  3. 2022Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processingcited by 16
  4. 2022LPF-Defense: 3D Adversarial Defense based on Frequency Analysiscited by 10
  5. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  6. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  7. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  8. 2023Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videoscited by 4
  9. 2024iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itselfcited by 4
  10. 2024Joint Top-Down and Bottom-Up Frameworks for 3D Visual Groundingcited by 3
  11. 2023Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Networkcited by 1
  12. 2024Eidos: Efficient, Imperceptible Adversarial 3D Point Cloudscited by 1
7 more
  1. 20253D Test-time Adaptation via Graph Spectral Driven Point Shiftcited by 1
  2. 2026STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understandingcited by 1
  3. 2024Hard-Label Black-Box Attacks on 3D Point Cloudscited by 0
  4. 2025Rethinking Gradient-based Adversarial Attacks on Point Cloud Classificationcited by 0
  5. 2025Learning from Few Samples: A Novel Approach for High-Quality Malcode Generationcited by 0
  6. 2026Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domaincited by 0
  7. 2026Geometry-Preserving Blind Watermarking for Raw 3D Point Cloudscited by 0