mlsanityData to 7 Oct 2026

On Adversarial Robustness of Point Cloud Semantic Segmentation

arXiv 2112.05871 ↗First posted 11 Dec 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent research efforts on 3D point cloud semantic segmentation (PCSS) have achieved outstanding performance by adopting neural networks. However, the robustness of these complex models have not been systematically analyzed. Given that PCSS has been applied in many safety-critical applications like autonomous driving, it is important to fill this knowledge gap, especially, how these models are affected under adversarial samples. As such, we present a comparative study of PCSS robustness. First, we formally define the attacker's objective under performance degradation and object hiding. Then, we develop new attack by whether to bound the norm. We evaluate different attack options on two datasets and three PCSS models. We found all the models are vulnerable and attacking point color is more effective. With this study, we call the attention of the research community to develop new approaches to harden PCSS models.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 11 Dec 2021.

Builds on

43 of 66 references.

References · 43

  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. 2020Point Transformercited by 1,462
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020PCT: Point cloud transformercited by 730
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
31 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  4. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  5. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  6. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  7. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  8. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  9. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  10. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  11. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  12. 2018Generating 3D Adversarial Point Cloudscited by 144
  13. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  14. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  15. 2018PointCloud Saliency Mapscited by 112
  16. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  17. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  18. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  19. 2021Towards Transferable Adversarial Attacks on Vision Transformerscited by 80
  20. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  21. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  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. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  26. 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
  27. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  28. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  29. 2019Adversarial Attack Generation Empowered by Min-Max Optimizationcited by 32
  30. 2019Indirect Local Attacks for Context-aware Semantic Segmentation Networkscited by 23
  31. 2020On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attackscited by 10

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attackscited by 0
  2. 2025Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 0
  3. 2025AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fieldscited by 0