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，诸如MidJourney和Stable Diffusion等文本到图像扩散模型，已对专业艺术家群体构成威胁。特别是，模型在基于艺术家作品样本进行"微调"后，能够学习模仿特定艺术家的艺术风格。本文描述了一种名为Glaze的工具的设计、实现与评估，该工具使艺术家能够在在线分享作品前为其应用"风格伪装"。这些伪装对图像施加几乎不可察觉的扰动，当被用作训练数据时，会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协作，针对超过1000名艺术家开展了用户研究，评估他们对AI艺术的看法、我们工具的效能、可用性及扰动容忍度，以及在不同场景下和面对自适应反制措施时的鲁棒性。调查结果与基于CLIP的实证得分均表明，即便在低扰动水平（p=0.05）下，Glaze在正常条件下（>92%）及面对自适应反制措施（>85%）时，都能高度有效地破坏风格模仿。