.png){kind=icon}
Return
Targeted attack via adversarial patch outside bounding box
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112244.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposing a stealthy targeted attack method for the physical world. • Enhancing the success rate of targeted attacks via adversarial patch outside bounding box. • Physical experiments show that our patches still exhibit superior performance across varying angles, devices, and distances.
Keywords:
stealthy targeted attack
adversarial patch
physical world
success rate enhancement
robustness across conditions
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations
Cited Papers
Deep learning-enhanced environment perception for autonomous driving: MDNet with CSP-DarkNet53.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveQuery-efficient black-box ensemble attack via dynamic surrogate weightingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSave no more