Diffusion Models

MASQUE: Diffusion-Based Localized Adversarial Makeup for Facial Privacy
We introduce MASQUE, a diffusion-based framework that generates localized adversarial makeup guided by user-defined text prompts.
Youngjin Kwon, Xiao Zhang
PDF Cite ArXiv OpenReview
DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
We propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination.
Jia Fu, Xiao Zhang, Sepideh Pashami, Fatemeh Rahimian, Anders Holst
Cite ArXiv