Appearing Attacks on LiDAR-Based 3D Object Detectors

Xiaowei Lin; Zhaoliang Wang; Chunyan Wang; Jianfeng Wang

doi:10.1007/978-981-95-8620-2_45

Appearing Attacks on LiDAR-Based 3D Object Detectors

Xiaowei Lin
, Zhaoliang Wang
, Chunyan Wang
, Jianfeng Wang^*

^*Corresponding author for this work

Harbin Institute of Technology Weihai
Shandong Institute of Innovation and Development
Weihai Institute of Education and Teaching Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

LiDAR is pivotal for the perception and safety of autonomous vehicles (AVs). Recent research indicates that the outputs of object detectors can be deliberately manipulated through carefully designed perturbations to the input data. This study introduces a novel attack methodology, termed the “appearing attack”, which induces object detectors to generate erroneous results by strategically incorporating specific features into the input data. To validate the feasibility and transferability of this attack, we conducted experiments using random parameter settings. Subsequently, we refined the approach through optimal parameter appearing attacks to maximize the effectiveness of this strategy.

Original language	English
Title of host publication	Resilience Transportation and Mobility Safety
Editors	Wuhong Wang, Yusheng Ci, Xiaowei Hu, Haiqiu Tan, Min Li
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	626-638
Number of pages	13
ISBN (Print)	9789819586196
DOIs	https://doi.org/10.1007/978-981-95-8620-2_45
State	Published - 2026
Externally published	Yes
Event	16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025 - Shanghai, China Duration: 9 May 2025 → 11 May 2025

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1607 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025
Country/Territory	China
City	Shanghai
Period	9/05/25 → 11/05/25

Keywords

3D object detection
adversarial attacks
autonomous driving

Access to Document

10.1007/978-981-95-8620-2_45

Cite this

Lin, X., Wang, Z., Wang, C., & Wang, J. (2026). Appearing Attacks on LiDAR-Based 3D Object Detectors. In W. Wang, Y. Ci, X. Hu, H. Tan, & M. Li (Eds.), Resilience Transportation and Mobility Safety (pp. 626-638). (Lecture Notes in Electrical Engineering; Vol. 1607 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-8620-2_45

@inproceedings{4db929ca04454329a05cbfc02e1a5a9f,

title = "Appearing Attacks on LiDAR-Based 3D Object Detectors",

abstract = "LiDAR is pivotal for the perception and safety of autonomous vehicles (AVs). Recent research indicates that the outputs of object detectors can be deliberately manipulated through carefully designed perturbations to the input data. This study introduces a novel attack methodology, termed the {\textquotedblleft}appearing attack{\textquotedblright}, which induces object detectors to generate erroneous results by strategically incorporating specific features into the input data. To validate the feasibility and transferability of this attack, we conducted experiments using random parameter settings. Subsequently, we refined the approach through optimal parameter appearing attacks to maximize the effectiveness of this strategy.",

keywords = "3D object detection, adversarial attacks, autonomous driving",

author = "Xiaowei Lin and Zhaoliang Wang and Chunyan Wang and Jianfeng Wang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025 ; Conference date: 09-05-2025 Through 11-05-2025",

year = "2026",

doi = "10.1007/978-981-95-8620-2\_45",

language = "英语",

isbn = "9789819586196",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "626--638",

editor = "Wuhong Wang and Yusheng Ci and Xiaowei Hu and Haiqiu Tan and Min Li",

booktitle = "Resilience Transportation and Mobility Safety",

address = "德国",

}

Lin, X, Wang, Z, Wang, C & Wang, J 2026, Appearing Attacks on LiDAR-Based 3D Object Detectors. in W Wang, Y Ci, X Hu, H Tan & M Li (eds), Resilience Transportation and Mobility Safety. Lecture Notes in Electrical Engineering, vol. 1607 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 626-638, 16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025, Shanghai, China, 9/05/25. https://doi.org/10.1007/978-981-95-8620-2_45

Appearing Attacks on LiDAR-Based 3D Object Detectors. / Lin, Xiaowei; Wang, Zhaoliang; Wang, Chunyan et al.
Resilience Transportation and Mobility Safety. ed. / Wuhong Wang; Yusheng Ci; Xiaowei Hu; Haiqiu Tan; Min Li. Springer Science and Business Media Deutschland GmbH, 2026. p. 626-638 (Lecture Notes in Electrical Engineering; Vol. 1607 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Appearing Attacks on LiDAR-Based 3D Object Detectors

AU - Lin, Xiaowei

AU - Wang, Zhaoliang

AU - Wang, Chunyan

AU - Wang, Jianfeng

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - LiDAR is pivotal for the perception and safety of autonomous vehicles (AVs). Recent research indicates that the outputs of object detectors can be deliberately manipulated through carefully designed perturbations to the input data. This study introduces a novel attack methodology, termed the “appearing attack”, which induces object detectors to generate erroneous results by strategically incorporating specific features into the input data. To validate the feasibility and transferability of this attack, we conducted experiments using random parameter settings. Subsequently, we refined the approach through optimal parameter appearing attacks to maximize the effectiveness of this strategy.

AB - LiDAR is pivotal for the perception and safety of autonomous vehicles (AVs). Recent research indicates that the outputs of object detectors can be deliberately manipulated through carefully designed perturbations to the input data. This study introduces a novel attack methodology, termed the “appearing attack”, which induces object detectors to generate erroneous results by strategically incorporating specific features into the input data. To validate the feasibility and transferability of this attack, we conducted experiments using random parameter settings. Subsequently, we refined the approach through optimal parameter appearing attacks to maximize the effectiveness of this strategy.

KW - 3D object detection

KW - adversarial attacks

KW - autonomous driving

UR - https://www.scopus.com/pages/publications/105043141763

U2 - 10.1007/978-981-95-8620-2_45

DO - 10.1007/978-981-95-8620-2_45

M3 - 会议稿件

AN - SCOPUS:105043141763

SN - 9789819586196

T3 - Lecture Notes in Electrical Engineering

SP - 626

EP - 638

BT - Resilience Transportation and Mobility Safety

A2 - Wang, Wuhong

A2 - Ci, Yusheng

A2 - Hu, Xiaowei

A2 - Tan, Haiqiu

A2 - Li, Min

PB - Springer Science and Business Media Deutschland GmbH

T2 - 16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025

Y2 - 9 May 2025 through 11 May 2025

ER -

Appearing Attacks on LiDAR-Based 3D Object Detectors

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this