EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LidarFooler: A Physical Backdoor Attack Method for LiDAR Point Cloud Classification

Wei Wang, Shaofei Yang, Jiawei Zhu, Yanze Ye, Yang Bai, Jinyin Chen iD

Sensors · 23.10.2026 · 26 (21) · 6722

DOI: 10.3390/s26216722 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.10.2026. Verfasst von Wei Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Electromagnetic Space Security, Jiaxing 314000, China. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Natural Science Foundation, National Natural Science Foundation of China, KeyLaboratoryof 559 the FifthResearchInstitute ofElectronics,Ministry of Industry andInformationTechnology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Light detection and ranging (LiDAR) point-cloud classifiers are vulnerable to backdoor poisoning, while physical sensing can disrupt triggers designed in the digital domain. We propose LidarFooler, a physical backdoor attack that uses a global trigger composed of multiple spatially distributed local trigger components to establish an association between the complete trigger pattern and an attacker-specified target class. Trigger centers are optimized using classification, geometric-preservation, and dispersion constraints, while expectation-over-transformation augmentation is employed to simulate physical variations during poisoned-sample generation. Extensive experiments on benchmark and physical-world datasets demonstrate the effectiveness and robustness of LidarFooler across different point-cloud classification settings. On digital data, LidarFooler achieves an average clean accuracy of 0.92 and an attack success rate of 0.93. Physical experiments with a Livox Mid-40 sensor achieve corresponding values of 0.93 and 0.86, respectively, with a mean attack success improvement of 42.5 percentage points over IRBA. Further evaluations demonstrate the robustness of LidarFooler under different trigger configurations, poisoning rates, target classes, model architectures, augmentations, and defense strategies. These results reveal a practical physical backdoor vulnerability in LiDAR point-cloud classification and highlight the need for security evaluation and defenses that explicitly account for physical sensing conditions.

Schlagwörter

Stichwörter der Autor:innen

autonomous drivinglight detection and ranging (LiDAR)physical backdoor attackpoint-cloud classificationsensor security

Autor:innen und Institutionen

  • National Key Laboratory of Electromagnetic Space Security, Jiaxing 314000, China.
  • College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China.

ORCID-Profile: Jinyin Chen

Förderung

  • Zhejiang Provincial Natural Science Foundation
  • National Natural Science Foundation of China
  • KeyLaboratoryof 559 the FifthResearchInstitute ofElectronics,Ministry of Industry andInformationTechnology

Zitieren

APA

Wang, W., Yang, S., Zhu, J., Ye, Y., Bai, Y., & Chen, J. (2026). LidarFooler: A Physical Backdoor Attack Method for LiDAR Point Cloud Classification. Sensors, 26(21), 6722. https://doi.org/10.3390/s26216722

Vancouver

Wang W, Yang S, Zhu J, Ye Y, Bai Y, Chen J. LidarFooler: A Physical Backdoor Attack Method for LiDAR Point Cloud Classification. Sensors. 2026;26(21):6722. doi:10.3390/s26216722

BibTeX
@article{Wang2026,
  author = {Wang, Wei and Yang, Shaofei and Zhu, Jiawei and Ye, Yanze and Bai, Yang and Chen, Jinyin},
  title = {LidarFooler: A Physical Backdoor Attack Method for LiDAR Point Cloud Classification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6722},
  doi = {10.3390/s26216722}
}
Kostenlos starten →