Guardado en:
Detalles Bibliográficos
Autores principales: Ozden, Tarik Can, Kara, Ozgur, Akcin, Oguzhan, Zaman, Kerem, Srivastava, Shashank, Chinchali, Sandeep P., Rehg, James M.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.17957
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914304563871744
author Ozden, Tarik Can
Kara, Ozgur
Akcin, Oguzhan
Zaman, Kerem
Srivastava, Shashank
Chinchali, Sandeep P.
Rehg, James M.
author_facet Ozden, Tarik Can
Kara, Ozgur
Akcin, Oguzhan
Zaman, Kerem
Srivastava, Shashank
Chinchali, Sandeep P.
Rehg, James M.
contents Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, taking hours for small batches. To address these challenges, we introduce DiffVax, a scalable, lightweight, and optimization-free framework for image immunization, specifically designed to prevent diffusion-based editing. Our approach enables effective generalization to unseen content, reducing computational costs and cutting immunization time from days to milliseconds, achieving a speedup of 250,000x. This is achieved through a loss term that ensures the failure of editing attempts and the imperceptibility of the perturbations. Extensive qualitative and quantitative results demonstrate that our model is scalable, optimization-free, adaptable to various diffusion-based editing tools, robust against counter-attacks, and, for the first time, effectively protects video content from editing. More details are available in https://diffvax.github.io/ .
format Preprint
id arxiv_https___arxiv_org_abs_2411_17957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
Ozden, Tarik Can
Kara, Ozgur
Akcin, Oguzhan
Zaman, Kerem
Srivastava, Shashank
Chinchali, Sandeep P.
Rehg, James M.
Computer Vision and Pattern Recognition
Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, taking hours for small batches. To address these challenges, we introduce DiffVax, a scalable, lightweight, and optimization-free framework for image immunization, specifically designed to prevent diffusion-based editing. Our approach enables effective generalization to unseen content, reducing computational costs and cutting immunization time from days to milliseconds, achieving a speedup of 250,000x. This is achieved through a loss term that ensures the failure of editing attempts and the imperceptibility of the perturbations. Extensive qualitative and quantitative results demonstrate that our model is scalable, optimization-free, adaptable to various diffusion-based editing tools, robust against counter-attacks, and, for the first time, effectively protects video content from editing. More details are available in https://diffvax.github.io/ .
title DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17957