EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Ruoxi, Jin, Haibo, Liu, Yixin, Chen, Jinyin, Wang, Haohan, Sun, Lichao
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916362273685504
author Chen, Ruoxi
Jin, Haibo
Liu, Yixin
Chen, Jinyin
Wang, Haohan
Sun, Lichao
author_facet Chen, Ruoxi
Jin, Haibo
Liu, Yixin
Chen, Jinyin
Wang, Haohan
Sun, Lichao
contents Text-to-image diffusion models have emerged as an evolutionary for producing creative content in image synthesis. Based on the impressive generation abilities of these models, instruction-guided diffusion models can edit images with simple instructions and input images. While they empower users to obtain their desired edited images with ease, they have raised concerns about unauthorized image manipulation. Prior research has delved into the unauthorized use of personalized diffusion models; however, this problem of instruction-guided diffusion models remains largely unexplored. In this paper, we first propose a protection method EditShield against unauthorized modifications from such models. Specifically, EditShield works by adding imperceptible perturbations that can shift the latent representation used in the diffusion process, tricking models into generating unrealistic images with mismatched subjects. Our extensive experiments demonstrate EditShield's effectiveness among synthetic and real-world datasets. Besides, we found that EditShield performs robustly against various manipulation settings across editing types and synonymous instruction phrases.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12066
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
Chen, Ruoxi
Jin, Haibo
Liu, Yixin
Chen, Jinyin
Wang, Haohan
Sun, Lichao
Cryptography and Security
Computer Vision and Pattern Recognition
Text-to-image diffusion models have emerged as an evolutionary for producing creative content in image synthesis. Based on the impressive generation abilities of these models, instruction-guided diffusion models can edit images with simple instructions and input images. While they empower users to obtain their desired edited images with ease, they have raised concerns about unauthorized image manipulation. Prior research has delved into the unauthorized use of personalized diffusion models; however, this problem of instruction-guided diffusion models remains largely unexplored. In this paper, we first propose a protection method EditShield against unauthorized modifications from such models. Specifically, EditShield works by adding imperceptible perturbations that can shift the latent representation used in the diffusion process, tricking models into generating unrealistic images with mismatched subjects. Our extensive experiments demonstrate EditShield's effectiveness among synthetic and real-world datasets. Besides, we found that EditShield performs robustly against various manipulation settings across editing types and synonymous instruction phrases.
title EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
topic Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.12066