Imperceptible Protection against Style Imitation from Diffusion Models

TL;DR

This paper presents a novel image protection method against diffusion model style imitation that maintains high visual quality by using perceptual maps, difficulty prediction, and perceptual constraints, ensuring imperceptibility and effectiveness.

Contribution

It introduces a perceptual and difficulty-aware protection approach that significantly improves visual quality while effectively preventing style imitation.

Findings

Enhanced protection without visual quality degradation

Effective against diffusion model style imitation

Maintains high perceptual similarity to original images

Abstract

Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style imitation, most are accompanied by the degradation of artworks' visual quality. Recognizing the importance of maintaining this, we introduce a visually improved protection method while preserving its protection capability. To this end, we devise a perceptual map to highlight areas sensitive to human eyes, guided by instance-aware refinement, which refines the protection intensity accordingly. We also introduce a difficulty-aware protection by predicting how difficult the artwork is to protect and dynamically adjusting the intensity based on this. Lastly, we integrate a perceptual constraints bank to further improve the imperceptibility. Results show that our method substantially elevates the quality of the protected image without compromising on protection efficacy.