mlsanityData to 7 Oct 2026

LPF-Defense: 3D Adversarial Defense based on Frequency Analysis

arXiv 2202.11287 ↗First posted 23 Feb 2022cs.CV cs.CR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of adversarial attacks. Based on our analysis on the performance of existing adversarial attacks, more adversarial perturbations are found in the mid and high-frequency components of input data. Therefore, by suppressing the high-frequency content in the training phase, the models robustness against adversarial examples is improved. Experiments showed that the proposed defense method decreases the success rate of six attacks on PointNet, PointNet++ ,, and DGCNN models. In particular, improvements are achieved with an average increase of classification accuracy by 3.8 % on drop100 attack and 4.26 % on drop200 attack compared to the state-of-the-art methods. The method also improves models accuracy on the original dataset compared to other available methods.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 40 of its 66 references that are in the map. First posted on arXiv 23 Feb 2022.

Builds on

40 of 66 references.

References · 40

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  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. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  9. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  10. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  11. 2018Spherical CNNscited by 452
  12. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
28 more
  1. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  2. 2018Generating 3D Adversarial Point Cloudscited by 144
  3. 2018PointCloud Saliency Mapscited by 112
  4. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  5. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  6. 2018Low Frequency Adversarial Perturbationcited by 80
  7. 2019Adversarial Attack and Defense on Point Setscited by 63
  8. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  9. 2019On the Effectiveness of Low Frequency Perturbationscited by 56
  10. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  11. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  12. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  13. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  14. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  15. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  16. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  17. 2020Hold me tight! Influence of discriminative features on deep network boundariescited by 31
  18. 2020Towards Frequency-Based Explanation for Robust CNNcited by 29
  19. 2020ShapeAdv: Generating Shape-Aware Adversarial 3D Point Cloudscited by 20
  20. 2022Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attackscited by 19
  21. 2022Boosting 3D Adversarial Attacks with Attacking On Frequencycited by 18
  22. 2019Spectral-GANs for High-Resolution 3D Point-cloud Generationcited by 17
  23. 2020Hypergraph Spectral Analysis and Processing in 3D Point Cloudcited by 14
  24. 2020On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attackscited by 10
  25. 2021Adversarial Attack by Limited Point Cloud Surface Modificationscited by 6
  26. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  27. 2019Adversarial shape perturbations on 3D point cloudscited by 3
  28. 2021Generating Unrestricted 3D Adversarial Point Cloudscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

10 papers.

  1. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  2. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  3. 2024iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itselfcited by 4
  4. 2022SAGA: Spectral Adversarial Geometric Attack on 3D Meshescited by 2
  5. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  6. 2022PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attackcited by 1
  7. 2024Invariance-powered Trustworthy Defense via Remove Then Restorecited by 0
  8. 2025Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attackscited by 0
  9. 2025KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Searchcited by 0
  10. 2026Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decompositioncited by 0