mlsanityData to 7 Oct 2026

Boosting 3D Adversarial Attacks with Attacking On Frequency

arXiv 2201.10937 ↗First posted 26 Jan 2022cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to SOTA 3D defense methods. Otherwise, compared to clean point clouds, adversarial point clouds obtained by AOF contain more deformation than outlier.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 26 Jan 2022.

Builds on

28 of 43 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
16 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  2. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  3. 2019Simple Black-box Adversarial Attackscited by 249
  4. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  5. 2018Generating 3D Adversarial Point Cloudscited by 144
  6. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  7. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  8. 2019Adversarial Attack and Defense on Point Setscited by 63
  9. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  10. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  11. 20183D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Modelcited by 47
  12. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  13. 2020Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNetcited by 45
  14. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  15. 2018Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Predictioncited by 5
  16. 2020Frequency-Tuned Universal Adversarial Attackscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 3; 2024: 2; 2025: 5; 2026: 2.

18 papers.

Sort:

  1. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  2. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  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. 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusioncited by 8
  6. 2022Improving transferability of 3D adversarial attacks with scale and shear transformationscited by 5
  7. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  8. 2023Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examplescited by 4
  9. 2025NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundarycited by 2
  10. 2025Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidancecited by 2
  11. 2022Adversarial samples for deep monocular 6D object pose estimationcited by 1
  12. 2024Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approachcited by 1
6 more
  1. 2025Transferable and Undefendable Point Cloud Attacks via Medial Axis Transformcited by 1
  2. 2022Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbationscited by 0
  3. 2025Rethinking Gradient-based Adversarial Attacks on Point Cloud Classificationcited by 0
  4. 2025KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Searchcited by 0
  5. 2026Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspectivecited by 0
  6. 2026Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Cloudscited by 0