Recent text-to-image diffusion models such as MidJourney and Stable Diffusion threaten to displace many in the professional artist community. In particular, models can learn to mimic the artistic style of specific artists after "fine-tuning" on samples of their art. In this paper, we describe the design, implementation and evaluation of Glaze, a tool that enables artists to apply "style cloaks" to their art before sharing online. These cloaks apply barely perceptible perturbations to images, and when used as training data, mislead generative models that try to mimic a specific artist. In coordination with the professional artist community, we deploy user studies to more than 1000 artists, assessing their views of AI art, as well as the efficacy of our tool, its usability and tolerability of perturbations, and robustness across different scenarios and against adaptive countermeasures. Both surveyed artists and empirical CLIP-based scores show that even at low perturbation levels (p=0.05), Glaze is highly successful at disrupting mimicry under normal conditions (>92%) and against adaptive countermeasures (>85%).

翻译：近期如MidJourney和Stable Diffusion等文本到图像扩散模型，威胁到专业艺术家群体的生存空间。特别是，模型可通过在艺术家作品样本上进行“微调”来模仿特定艺术家的艺术风格。本文描述了Glaze工具的设计、实现与评估，该工具使艺术家在上传作品前能对其施加“风格斗篷”。这些斗篷通过引入人眼几乎无法察觉的扰动，在用作训练数据时，能误导试图模仿特定艺术家的生成模型。我们与专业艺术家群体合作，对超过1000名艺术家进行了用户研究，评估他们对AI艺术的看法，以及我们工具的有效性、可用性、扰动容忍度，以及在不同场景下和针对适应性反制措施的鲁棒性。调查结果显示，即使在低扰动水平（p=0.05）下，Glaze在正常条件下（>92%）和针对适应性反制措施（>85%）均能高效破坏模仿行为，这一结论得到了受访艺术家和基于CLIP的实证评分的一致支持。