.png){kind=icon}
.png){kind=icon}
Return
DiffProtect: Generative adversarial examples using diffusion models for facial privacy protection
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2025.112780.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Diffusion model-based adversarial attacks for facial privacy protection with high visual quality. • Face semantics regularization module preserves visual identity during facial privacy protection. • Attack acceleration strategy significantly improves efficiency while maintaining performance. • 24.5 % absolute improvement in attack success rate compared to state-of-the-art methods. • Real-world validation with commercial API and user study shows practical effectiveness.
Keywords:
Facial privacy
Diffusion models
Adversarial attack
Face recognition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations