Is Perturbation-Based Image Protection Disruptive to Image Editing?

TL;DR

Perturbation-based image protection methods are insufficient against diffusion-based editing, as protected images can still produce desirable outputs, and noise addition may inadvertently enhance image-editing success.

Contribution

This study critically evaluates existing perturbation-based image protection techniques and reveals their limitations in preventing diffusion model-based image editing.

Findings

Protection methods often fail to prevent desired edits.

Adding noise can increase image association with prompts.

Perturbation methods may not be reliable for robust protection.

Abstract

The remarkable image generation capabilities of state-of-the-art diffusion models, such as Stable Diffusion, can also be misused to spread misinformation and plagiarize copyrighted materials. To mitigate the potential risks associated with image editing, current image protection methods rely on adding imperceptible perturbations to images to obstruct diffusion-based editing. A fully successful protection for an image implies that the output of editing attempts is an undesirable, noisy image which is completely unrelated to the reference image. In our experiments with various perturbation-based image protection methods across multiple domains (natural scene images and artworks) and editing tasks (image-to-image generation and style editing), we discover that such protection does not achieve this goal completely. In most scenarios, diffusion-based editing of protected images generates a desirable output image which adheres precisely to the guidance prompt. Our findings suggest that adding noise to images may paradoxically increase their association with given text prompts during the generation process, leading to unintended consequences such as better resultant edits. Hence, we argue that perturbation-based methods may not provide a sufficient solution for robust image protection against diffusion-based editing.