GLEAN: Generative Learning for Eliminating Adversarial Noise
This work addresses ethical issues in digital art protection by analyzing and enhancing existing tools, but it is incremental as it builds directly on Glaze without introducing a fundamentally new approach.
The paper tackles the problem of style mimicry attacks on digital art using diffusion models by proposing GLEAN, a method that applies image-to-image generative networks to remove perturbations from Glaze-protected images, evaluating its effectiveness in restoring attack performance.
In the age of powerful diffusion models such as DALL-E and Stable Diffusion, many in the digital art community have suffered style mimicry attacks due to fine-tuning these models on their works. The ability to mimic an artist's style via text-to-image diffusion models raises serious ethical issues, especially without explicit consent. Glaze, a tool that applies various ranges of perturbations to digital art, has shown significant success in preventing style mimicry attacks, at the cost of artifacts ranging from imperceptible noise to severe quality degradation. The release of Glaze has sparked further discussions regarding the effectiveness of similar protection methods. In this paper, we propose GLEAN- applying I2I generative networks to strip perturbations from Glazed images, evaluating the performance of style mimicry attacks before and after GLEAN on the results of Glaze. GLEAN aims to support and enhance Glaze by highlighting its limitations and encouraging further development.