mlsanityData to 7 Oct 2026

Adversarial Attack and Defense on Point Sets

arXiv 1902.10899 ↗First posted 28 Feb 2019cs.CV cs.AI cs.CRcited by 63

Not on the map. Why?

Abstract (arXiv)

Emergence of the utility of 3D point cloud data in safety-critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point cloud data to detect potential attack data or noisy sensing data. Notably, the proposed defense methods are even effective to detect the adversarial point clouds generated by a proof-of-concept attack directly targeting the defense. Transferability of adversarial attacks between several point cloud networks is addressed, and we propose an momentum-enhanced pointwise gradient to improve the attack transferability. We further analyze the transferability from adversarial point clouds to grid CNNs and the inverse. Extensive experimental results on common point cloud benchmarks demonstrate the validity of the proposed 3D attack and defense framework.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 17; 2023: 9; 2024: 10; 2025: 6; 2026: 4.

63 papers.

Sort:

By area:

  1. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  2. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  3. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  4. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  5. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  6. 2021Fooling LiDAR Perception via Adversarial Trajectory Perturbationcited by 25
  7. 2022Imperceptible and Robust Backdoor Attack in 3D Point Cloudcited by 25
  8. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  9. 2022Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attackscited by 19
  10. 2022Boosting 3D Adversarial Attacks with Attacking On Frequencycited by 18
  11. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  12. 2021Adversarial Attacks on Camera-LiDAR Models for 3D Car Detectioncited by 16
38 more
  1. 2021Robustness Certification for Point Cloud Modelscited by 16
  2. 2022Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processingcited by 16
  3. 2024Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Needcited by 16
  4. 2021Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Modelscited by 14
  5. 2022OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Datacited by 13
  6. 2022ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotationcited by 12
  7. 2022LPF-Defense: 3D Adversarial Defense based on Frequency Analysiscited by 10
  8. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9
  9. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  10. 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusioncited by 8
  11. 2021Poisoning MorphNet for Clean-Label Backdoor Attack to Point Cloudscited by 7
  12. 2021Local Aggressive Adversarial Attacks on 3D Point Cloudcited by 7
  13. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  14. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  15. 2021The art of defense: letting networks fool the attackercited by 6
  16. 2021Adversarial Attack by Limited Point Cloud Surface Modificationscited by 6
  17. 2023PointCert: Point Cloud Classification with Deterministic Certified Robustness Guaranteescited by 6
  18. 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6
  19. 2023Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptionscited by 6
  20. 20223DVerifier: Efficient Robustness Verification for 3D Point Cloud Modelscited by 5
  21. 2022Improving transferability of 3D adversarial attacks with scale and shear transformationscited by 5
  22. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  23. 2022Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shapecited by 4
  24. 20233D Adversarial Augmentations for Robust Out-of-Domain Predictionscited by 4
  25. 2021On Adversarial Robustness of Point Cloud Semantic Segmentationcited by 3
  26. 2024A Survey on Adversarial Robustness of LiDAR-based Machine Learning Perception in Autonomous Vehiclescited by 3
  27. 20213D Point Cloud Completion with Geometric-Aware Adversarial Augmentationcited by 2
  28. 2021Generating Unrestricted 3D Adversarial Point Cloudscited by 2
  29. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  30. 2024Robust 3D Point Clouds Classification based on Declarative Defenderscited by 2
  31. 2025Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidancecited by 2
  32. 2023SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectorscited by 1
  33. 2024Eidos: Efficient, Imperceptible Adversarial 3D Point Cloudscited by 1
  34. 2024Adversarial 3D Virtual Patches using Integrated Gradientscited by 1
  35. 2024LiDAttack: Robust Black-box Attack on LiDAR-based Object Detectioncited by 1
  36. 2025Transferable and Undefendable Point Cloud Attacks via Medial Axis Transformcited by 1
  37. 2025Generating Adversarial Point Clouds Using Diffusion Modelcited by 1
  38. 2022Learning to Censor by Noisy Samplingcited by 0

50 most cited of 63 All 63 (JSON)