PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification
Not on the map. Why?
Abstract (arXiv)
Point clouds are extensively employed in a variety of real-world applications such as robotics, autonomous driving and augmented reality. Despite the recent success of point cloud neural networks, especially for safety-critical tasks, it is essential to also ensure the robustness of the model. A typical way to assess a model's robustness is through adversarial attacks, where test-time examples are generated based on gradients to deceive the model. While many different defense mechanisms are studied in 2D, studies on 3D point clouds have been relatively limited in the academic field. Inspired from PointDP, which denoises the network inputs by diffusion, we propose Point Cloud Layerwise Diffusion (PCLD), a layerwise diffusion based 3D point cloud defense strategy. Unlike PointDP, we propagated the diffusion denoising after each layer to incrementally enhance the results. We apply our defense method to different types of commonly used point cloud models and adversarial attacks to evaluate its robustness. Our experiments demonstrate that the proposed defense method achieved results that are comparable to or surpass those of existing methodologies, establishing robustness through a novel technique. Code is available at https://github.com/batuceng/diffusion-layer-robustness-pc.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 11 Mar 2024.
Builds on
27 of 43 references.
References · 27
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2013Intriguing properties of neural networkscited by 5,155
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
- 2016Adversarial examples in the physical worldcited by 1,769
- 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
- 2020PCT: Point cloud transformercited by 732
15 more
- 2022Diffusion Models for Adversarial Purificationcited by 476
- 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
- 2018PU-Net: Point Cloud Upsampling Networkcited by 209
- 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
- 2018Generating 3D Adversarial Point Cloudscited by 144
- 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
- 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
- 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
- 2018PointCloud Saliency Mapscited by 112
- 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
- 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
- 20214D Panoptic LiDAR Segmentationcited by 65
- 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
- 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
- 2019Large-scale 3D point cloud representations via graph inception networks with applications to autonomous drivingcited by 8
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.