按年被提到
20212021 · 1 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:2107.06018 · cs.CV

This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces

Ryan Webster, Julien Rabin, Loic Simon, Frederic Jurie · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2021-10-14 · 最近 2022-11-01
2不同的人
2活跃月份
2讨论串
23被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website {\small \url{ http://thispersondoesnotexist.com}}, taunts users with GAN generated images that seem too real to believe. On the other hand, GANs do leak information about their training data, as evidenced by membership attacks recently demonstrated in the literature. In this work, we challenge the assumption that GAN faces really are novel creations, by constructing a successful membership attack of a new kind. Unlike previous works, our attack can accurately discern samples sharing the same identity as training samples without being the same samples. We demonstrate the interest of our attack across several popular face datasets and GAN training procedures. Notably, we show that even in the presence of significant dataset diversity, an over represented person can pose a privacy concern.

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godelski · 2022-11

“I'm an AI researcher working on generative modeling, so I want to note my bias upfront. But I'm also a musician/artist and so I find some of these conversations odd. The problem with them I see is that they are oversimplified. To get better at drawing I often copy other works. Or I'll play a piece exactly as intended. Then I get more advanced and learn a…”

An unwilling illustrator found herself turned into an AI model原评论 ↗
被提交为 story · 1 次