mlsanityData to 7 Oct 2026

Physically Realizable Adversarial Examples for LiDAR Object Detection

arXiv 2004.00543 ↗First posted 1 Apr 2020cs.CV cs.CR cs.LGcited by 137

Not on the map. Why?

Abstract (arXiv)

Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Despite the fact that this poses a security concern for the self-driving industry, there has been very little exploration in terms of 3D perception, as most adversarial attacks have only been applied to 2D flat images. In this paper, we address this issue and present a method to generate universal 3D adversarial objects to fool LiDAR detectors. In particular, we demonstrate that placing an adversarial object on the rooftop of any target vehicle to hide the vehicle entirely from LiDAR detectors with a success rate of 80%. We report attack results on a suite of detectors using various input representation of point clouds. We also conduct a pilot study on adversarial defense using data augmentation. This is one step closer towards safer self-driving under unseen conditions from limited training data.

Key facts. Cited by 137 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 30; 2023: 30; 2024: 18; 2025: 14; 2026: 17.

137 papers.

Sort:

By area:

  1. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 136
  2. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  3. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  4. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  5. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  6. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  7. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  8. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  9. 2022Shape-invariant 3D Adversarial Point Cloudscited by 49
  10. 2021Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Drivingcited by 45
  11. 2021Optical Adversarial Attackcited by 43
  12. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
38 more
  1. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  2. 2023RoboBEV: Towards Robust Bird's Eye View Perception under Corruptionscited by 42
  3. 2021Vehicle trajectory prediction works, but not everywherecited by 39
  4. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  5. 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
  6. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  7. 2021Cross-modal Adversarial Reprogrammingcited by 34
  8. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 34
  9. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  10. 2022V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perceptioncited by 28
  11. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  12. 2023CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulationcited by 26
  13. 2021Fooling LiDAR Perception via Adversarial Trajectory Perturbationcited by 25
  14. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  15. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  16. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  17. 2022Physical-World Optical Adversarial Attacks on 3D Face Recognitioncited by 23
  18. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  19. 2022A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attackscited by 22
  20. 2021CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generationcited by 20
  21. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  22. 2022A Survey of Neural Trojan Attacks and Defenses in Deep Learningcited by 17
  23. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  24. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  25. 2021Adversarial Attacks on Camera-LiDAR Models for 3D Car Detectioncited by 16
  26. 2024HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Textcited by 16
  27. 2021Object Removal Attacks on LiDAR-based 3D Object Detectorscited by 15
  28. 2023On the Adversarial Robustness of Camera-based 3D Object Detectioncited by 15
  29. 2023Physical Adversarial Attacks for Surveillance: A Surveycited by 15
  30. 2021Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Modelscited by 14
  31. 2024CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perceptioncited by 13
  32. 2022Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attackscited by 12
  33. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  34. 2023Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detectioncited by 11
  35. 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasurescited by 11
  36. 2022PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognitioncited by 10
  37. 2023Adv3D: Generating 3D Adversarial Examples for 3D Object Detection in Driving Scenarios with NeRFcited by 10
  38. 2023Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulationcited by 10

50 most cited of 137 All 137 (JSON)