mlsanityData to 14 Oct 2026

Adversarial 3D Virtual Patches using Integrated Gradients

arXiv 2406.00282 ↗First posted 1 Jun 2024cs.CV cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 1 Jun 2024.

Builds on

21 of 30 references.

References · 21

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  3. 2018Sanity Checks for Saliency Mapscited by 1,156
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  5. 2017Adversarial Patchcited by 517
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
  8. 2018PointCloud Saliency Mapscited by 112
  9. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  10. 2021Improving Transferability of Adversarial Patches on Face Recognition with Generative Modelscited by 80
  11. 2019Adversarial Attack and Defense on Point Setscited by 63
  12. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
9 more
  1. 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
  2. 2022You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworkscited by 32
  3. 2016Gradients of Counterfactualscited by 31
  4. 2021Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehiclescited by 26
  5. 2019Design and Interpretation of Universal Adversarial Patches in Face Detectioncited by 23
  6. 2021Object Removal Attacks on LiDAR-based 3D Object Detectorscited by 16
  7. 2021Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perceptioncited by 8
  8. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  9. 2023ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistencycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectorscited by 0