arrow
返回

Object-fabrication targeted attack for object detection

delete2025-04-01
delete0
PRE
AI
张
张续冲 (Xuchong Zhang) *
C
Changfeng Sun
H
Haoliang Han
孙
孙宏滨 (Hongbin Sun)
DOI:10.1016/j.neucom.2025.129561delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Recent studies have demonstrated that object detection networks are usually vulnerable to adversarial examples. Generally, adversarial attacks for object detection can be categorized into targeted and untargeted attacks. Compared with untargeted attacks, targeted attacks present greater challenges and all existing targeted attack methods launch the attack by misleading detectors to mislabel the detected object as a specific wrong label. However, since these methods must depend on the presence of the detected objects within the victim image, they suffer from limitations in attack scenarios and attack success rates. In this paper, we propose targeted feature space attack method that can mislead detectors to 'fabricate' extra designated objects regardless of whether the victim image contains objects or not. Specifically, we introduce a guided image to extract coarse-grained features of the target objects and design an innovative dual attention mechanism to filter out the critical features of the target objects efficiently. The attack performance of the proposed method is evaluated on MS COCO and BDD100K datasets with FasterRCNN and YOLOv5. Evaluation results indicate that the proposed targeted feature space attack method shows significant improvements in terms of image-specific, universality, and generalization attack performance, compared with the previous targeted attack for object detection.
Keyword:
Targeted attack
Object detection
Feature attack

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

X
xi'an jiaotong university
学者数:
9.3W
论文数: 6.7W
被引数: 75
引用论文

引用论文

err分享
err收藏
err分享
err收藏
Life history of the codling moth in the Yakima Valley of Washington /
err
IF0
err1924-01-01
err0
errOAAI
errE. J. Newcomer; W. D. Whitcomb
err分享
err收藏
err
IF0
err1900-01-01
err0
PREAI
err
err分享
err收藏
err分享
err收藏
err分享
err收藏
学者 查看更多内容