按年被提到
20232023 · 4 次2026
视觉、语音与图像生成›图像与视频生成·arXiv:2302.04222 · cs.CR

Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models

Shawn Shan, Jenna Cryan, Emily Wenger, Haitao Zheng, Rana Hanocka, Ben Y. Zhao · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2023-02-14 · 最近 2023-03-20
4不同的人
2活跃月份
4讨论串
90被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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%).

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论Kim_Bruning · 2023-03

“I'm actually just summarizing what the sources say here. "Plagiarism is the fraudulent representation of another person's language, thoughts, ideas, or expressions as one's own original work." [1] Tool claims to prevent plagiarism, paper uses "plagiarism" language throughout. [2] Writers of tool used substantial portions of a different tool without ack…”

Glaze (Poisoning AI Artists)原评论 ↗
被提交为 story · 3 次