Lune

S&P2023Top-tier venue

PLA-LiDAR: Physical Laser Attacks against LiDAR-based 3D Object Detection in Autonomous Vehicle

Zizhi Jin, Xiaoyu Ji, Yushi Cheng, Bo Yang, Chen Yan, Wenyuan Xu

Abstract

Autonomous vehicles and robots increasingly exploit LiDAR-based 3D object detection systems to detect obstacles in environment. Correct detection and classification are important to ensure safe driving. Though existing work has demonstrated the feasibility of manipulating point clouds to spoof 3D object detectors, most of the attempts are conducted digitally. In this paper, we investigate the possibility of physically fooling LiDAR-based 3D object detection by injecting adversarial point clouds using lasers. First, we develop a laser transceiver that can inject up to 4200 points, which is 20 times more than prior work, and can measure the scanning cycle of victim LiDARs to schedule the spoofing laser signals. By designing a control signal method that converts the coordinates of point clouds to control signals and an adversarial point cloud optimization method with physical constraints of LiDARs and attack capabilities, we manage to inject spoofing point cloud with desired point cloud shapes into the victim LiDAR physically. We can launch four types of attacks, i.e., naive hiding, record-based creating, optimization-based hiding, and optimization-based creating. Extensive experiments demonstrate the effectiveness of our attacks against two commercial LiDAR and three detectors. We also discuss defense strategies at the sensor and AV system levels.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

24 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasures cites Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving?
  • On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasures cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • On Data Fabrication in Collaborative Vehicular Perception: Attacks and Countermeasures cites Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
  • Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving? cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving? cites Towards Evaluating the Robustness of Neural Networks
  • Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving? cites Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
  • Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving cites Towards Evaluating the Robustness of Neural Networks
  • AE-Morpher: Improve Physical Robustness of Adversarial Objects against LiDAR-based Detectors via Object Reconstruction cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • AE-Morpher: Improve Physical Robustness of Adversarial Objects against LiDAR-based Detectors via Object Reconstruction cites Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
  • Unity is Strength? Benchmarking the Robustness of Fusion-based 3D Object Detection against Physical Sensor Attack cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • Unity is Strength? Benchmarking the Robustness of Fusion-based 3D Object Detection against Physical Sensor Attack cites Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer Vision
  • A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving cites Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving?
  • A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving cites Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
  • Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks cites Towards Evaluating the Robustness of Neural Networks
  • Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer Vision cites Towards Evaluating the Robustness of Neural Networks
  • Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection cites Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
  • Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection cites Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers24

  1. Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionZhiyuan Cheng, Hongjun Choi, Shiwei Feng, James Chenhao Liang et al.ICLR 2024 · 32 citations
  2. On Data Fabrication in Collaborative Vehicular Perception: Attacks and CountermeasuresQingzhao Zhang, Shuowei Jin, Ruiyang Zhu, Jiachen Sun et al.USENIX Security 2024 · 25 citations
  3. AE-Morpher: Improve Physical Robustness of Adversarial Objects against LiDAR-based Detectors via Object ReconstructionShenchen Zhu, Yue Zhao, Kai Chen, Bo Wang et al.USENIX Security 2024 · 13 citations
  4. A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous DrivingYang Lou, Yi Zhu, Qun Song, Rui Tan et al.USENIX Security 2024 · 11 citations
  5. Unity is Strength? Benchmarking the Robustness of Fusion-based 3D Object Detection against Physical Sensor AttackZizhi Jin, Xuancun Lu, Bo Yang, Yushi Cheng et al.WWW 2024 · 7 citations

Builds on7

  1. Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David A. WagnerS&P 2017 · 9,786 citations
  2. Adversarial Sensor Attack on LiDAR-based Perception in Autonomous DrivingYulong Cao, Chaowei Xiao, Benjamin Cyr, Yimeng Zhou et al.CCS 2019 · 626 citations
  3. Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World AttacksYulong Cao, Ningfei Wang, Chaowei Xiao, Dawei Yang et al.S&P 2021 · 309 citations
  4. Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer VisionXiaoyu Ji, Yushi Cheng, Yuepeng Zhang, Kai Wang et al.S&P 2021 · 99 citations
  5. Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving?Yi Zhu, Chenglin Miao, Tianhang Zheng, Foad Hajiaghajani et al.CCS 2021 · 65 citations

Related papers

  1. Physically Realizable Adversarial Examples for LiDAR Object DetectionJames Tu, Mengye Ren, Sivabalan Manivasagam, Ming Liang et al.CVPR 2020
  2. You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving FrameworksYulong Cao, S. Hrushikesh Bhupathiraju, Pirouz Naghavi, Takeshi Sugawara et al.USENIX Security 2023
  3. Towards Real-Time Defense against Object-Based LiDAR Attacks in Autonomous DrivingYan Zhang, Zihao Liu, Yi Zhu, Chenglin MiaoCCS 2025
  4. LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack StrategiesTakami Sato, Yuki Hayakawa, Ryo Suzuki, Yohsuke Shiiki et al.NDSS 2024
  5. Fooling LiDAR Perception via Adversarial Trajectory PerturbationYiming Li, Congcong Wen, Felix Juefei-Xu, Chen FengICCV 2021 · 69 citations
Dusk over the sea between two cliffs drawn in fine vertical lines