mlsanityData to 14 Oct 2026

Adversarial Attack by Limited Point Cloud Surface Modifications

arXiv 2110.03745 ↗First posted 7 Oct 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent research has revealed that the security of deep neural networks that directly process 3D point clouds to classify objects can be threatened by adversarial samples. Although existing adversarial attack methods achieve high success rates, they do not restrict the point modifications enough to preserve the point cloud appearance. To overcome this shortcoming, two constraints are proposed. These include applying hard boundary constraints on the number of modified points and on the point perturbation norms. Due to the restrictive nature of the problem, the search space contains many local maxima. The proposed method addresses this issue by using a high step-size at the beginning of the algorithm to search the main surface of the point cloud fast and effectively. Then, in order to converge to the desired output, the step-size is gradually decreased. To evaluate the performance of the proposed method, it is run on the ModelNet40 and ScanObjectNN datasets by employing the state-of-the-art point cloud classification models; including PointNet, PointNet++, and DGCNN. The obtained results show that it can perform successful attacks and achieve state-of-the-art results by only a limited number of point modifications while preserving the appearance of the point cloud. Moreover, due to the effective search algorithm, it can perform successful attacks in just a few steps. Additionally, the proposed step-size scheduling algorithm shows an improvement of up to 14.5% when adopted by other methods as well. The proposed method also performs effectively against popular defense methods.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

24 of 35 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  12. 2018Generating 3D Adversarial Point Cloudscited by 144
12 more
  1. 2017Pointwise Convolutional Neural Networkscited by 127
  2. 2018PointCloud Saliency Mapscited by 112
  3. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  4. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  5. 2019Adversarial Attack and Defense on Point Setscited by 63
  6. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  7. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  8. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  9. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  10. 2018Unrestricted Adversarial Examplescited by 40
  11. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  12. 2019Adversarial shape perturbations on 3D point cloudscited by 3

Built on by

Cited by year

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

6 papers.

  1. 2022LPF-Defense: 3D Adversarial Defense based on Frequency Analysiscited by 10
  2. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  3. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  4. 2024LiDAttack: Robust Black-box Attack on LiDAR-based Object Detectioncited by 1
  5. 2025Generating Adversarial Point Clouds Using Diffusion Modelcited by 1
  6. 2025KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Searchcited by 0