mlsanityData to 7 Oct 2026

Object Removal Attacks on LiDAR-based 3D Object Detectors

arXiv 2102.03722 ↗First posted 7 Feb 2021cs.CV cs.CR cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 9 of its 14 references that are in the map. First posted on arXiv 7 Feb 2021.

Builds on

9 of 14 references.

References · 9

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  3. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  4. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  5. 2018Generating 3D Adversarial Point Cloudscited by 144
  6. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  7. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  8. 2018Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networkscited by 21
  9. 2020Nudge Attacks on Point-Cloud DNNscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 2; 2024: 3; 2025: 1; 2026: 2.

15 papers.

Sort:

  1. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  2. 2023Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detectioncited by 11
  3. 2023LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategiescited by 9
  4. 2021Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perceptioncited by 7
  5. 2021Real-time Detection of Practical Universal Adversarial Perturbationscited by 6
  6. 2022Roadmap for Cybersecurity in Autonomous Vehiclescited by 5
  7. 2022Using 3D Shadows to Detect Object Hiding Attacks on Autonomous Vehicle Perceptioncited by 5
  8. 2021Jacobian Regularization for Mitigating Universal Adversarial Perturbationscited by 4
  9. 2022Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attackscited by 4
  10. 2024A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Drivingcited by 3
  11. 2025Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Drivingcited by 3
  12. 2024Adversarial 3D Virtual Patches using Integrated Gradientscited by 1
3 more
  1. 2024LiDAttack: Robust Black-box Attack on LiDAR-based Object Detectioncited by 1
  2. 2026Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectorscited by 0
  3. 2026Fast Object Removal Attacks on Safety-Critical Video-based Perception Systemscited by 0