Adversarial Patches for Fooling Positive-Negative Obstacle Detectors on Unstructured Roads

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Duan, Yijian;Meng, Liwen;Zhu, Jihong;Meng, Yanmei*;Liang, Yuan;...

通讯作者：

Meng, Yanmei;Liang, Y

作者机构：

[Liang, Yuan; Meng, Yanmei; Duan, Yijian; Meng, Liwen; Wu, Jiachun] Guangxi Univ, Coll Mech Engn, Nanning 530004, Guangxi, Peoples R China.

[Meng, Liwen] Hunan Univ, Natl Grad Coll Elite Engineers, Changsha 410082, Hunan, Peoples R China.

[Zhu, Jihong] Tsinghua Univ, Dept Precis Instrument, Beijing 100000, Peoples R China.

[Zhang, Jinlai] Changsha Univ Sci & Technol, Coll Automot & Mech Engn, Changsha 410114, Hunan, Peoples R China.

通讯机构：

[Liang, Y ; Meng, YM] G

Guangxi Univ, Coll Mech Engn, Nanning 530004, Guangxi, Peoples R China.

语种：

英文

关键词：

Perturbation methods;Roads;Optimization;Object detection;Robustness;Artificial neural networks;Simulated annealing;Intelligent sensors;Detectors;Shape;Adversarial patch;deep learning models;object detection;physical world;robustness

期刊：

IEEE Sensors Journal

ISSN：

1530-437X

年：

2025

卷：

期：

页码：

36466-36478

DOI：

10.1109/JSEN.2025.3586858

基金类别：

Guangxi key research and development project (Grant Number: Guike AB22080098) the Guangxi Science and Technology Major Project (Grant Number: Guike AA23023011) Guangxi Science and Technology Major Project (Grant Number: Guike AA23062040) National Natural Science Foundation Project (Grant Number: 52365001)

机构署名：

本校为其他机构

院系归属：

汽车与机械工程学院

摘要：

Adversarial patches represent a critical form of physical adversarial attacks, posing significant risks to the security of neural network-based object detection systems. Previous research on adversarial patches has predominantly focused on pedestrian detection, facial recognition, and vehicle detection, with limited attention to the detection of positive and negative obstacles on unstructured roads. Moreover, prior studies typically optimize perturbation information while fixing parameters such as the patch's position and rotation angle or manipulate parameters such as position and rotation an...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Adversarial Patches for Fooling Positive-Negative Obstacle Detectors on Unstructured Roads

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问