mlsanityData to 7 Oct 2026

A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

arXiv 2212.10230 ↗First posted 20 Dec 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed significant advancements in deep learning-based 3D object detection, leading to its widespread adoption in numerous applications. As 3D object detectors become increasingly crucial for security-critical tasks, it is imperative to understand their robustness against adversarial attacks. This paper presents the first comprehensive evaluation and analysis of the robustness of LiDAR-based 3D detectors under adversarial attacks. Specifically, we extend three distinct adversarial attacks to the 3D object detection task, benchmarking the robustness of state-of-the-art LiDAR-based 3D object detectors against attacks on the KITTI and Waymo datasets. We further analyze the relationship between robustness and detector properties. Additionally, we explore the transferability of cross-model, cross-task, and cross-data attacks. Thorough experiments on defensive strategies for 3D detectors are conducted, demonstrating that simple transformations like flipping provide little help in improving robustness when the applied transformation strategy is exposed to attackers. reviseFinally, we propose balanced adversarial focal training, based on conventional adversarial training, to strike a balance between accuracy and robustness. Our findings will facilitate investigations into understanding and defending against adversarial attacks on LiDAR-based 3D object detectors, thus advancing the field. The source code is publicly available at urlhttps://github.com/Eaphan/Robust3DOD.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 45 of its 83 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

45 of 83 references.

References · 45

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
33 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2017Countering Adversarial Images using Input Transformationscited by 517
  5. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  6. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  7. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  8. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  9. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  10. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  11. 2018Generating 3D Adversarial Point Cloudscited by 144
  12. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  13. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  14. 2018PointCloud Saliency Mapscited by 112
  15. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  16. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  17. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  18. 2020Intrinsic Certified Robustness of Bagging against Data Poisoning Attackscited by 90
  19. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  20. 2022LiDAR Snowfall Simulation for Robust 3D Object Detectioncited by 72
  21. 2022Point Density-Aware Voxels for LiDAR 3D Object Detectioncited by 70
  22. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  23. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  24. 2022SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectioncited by 52
  25. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  26. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  27. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  28. 2021Pyramid Adversarial Training Improves ViT Performancecited by 39
  29. 2021Imperceptible Transfer Attack and Defense on 3D Point Cloud Classificationcited by 36
  30. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  31. 2022GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimationcited by 24
  32. 2021Adversarial Attacks on Camera-LiDAR Models for 3D Car Detectioncited by 16
  33. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 9; 2026: 3.

22 papers.

Sort:

By area:

  1. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  2. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  3. 2023Unleash the Potential of Image Branch for Cross-modal 3D Object Detectioncited by 11
  4. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  5. 2024Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibrationcited by 7
  6. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  7. 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Modelscited by 5
  8. 2024Module-wise Adaptive Adversarial Training for End-to-end Autonomous Drivingcited by 4
  9. 2024Artificial Immune System of Secure Face Recognition Against Adversarial Attackscited by 2
  10. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  11. 2025Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attackscited by 1
  12. 2025SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectorscited by 1
10 more
  1. 2026Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detectioncited by 1
  2. 2024Hybrid Pooling and Convolutional Network for Improving Accuracy and Training Convergence Speed in Object Detectioncited by 0
  3. 2025Hi-ALPS -- An Experimental Robustness Quantification of Six LiDAR-based Object Detection Systems for Autonomous Drivingcited by 0
  4. 2025LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimationcited by 0
  5. 2025Robustifying 3D Perception via Least-Squares Graphs for Multi-Agent Object Trackingcited by 0
  6. 2025Deep Learning For Point Cloud Denoising: A Surveycited by 0
  7. 2025Efficient Model-Based Purification Against Adversarial Attacks for LiDAR Segmentationcited by 0
  8. 2025Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehiclescited by 0
  9. 2026Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detectioncited by 0
  10. 2026Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Drivingcited by 0