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