Is Perturbation-Based Image Protection Disruptive to Image Editing?
This reveals a critical flaw in current image protection techniques for preventing misuse of AI-generated content, highlighting an incremental but important security gap.
The paper investigates whether perturbation-based image protection methods effectively disrupt diffusion-based image editing, finding that in most scenarios, these methods fail to prevent desirable edits and may even improve them, with experiments showing unintended better results across domains like natural scenes and artworks.
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.