按年被提到
20182018 · 1 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:1802.06739 · cs.LG

Differentially Private Generative Adversarial Network

Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, Jiayu Zhou · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2018-02-26 · 最近 2023-01-11
2不同的人
2活跃月份
2讨论串
322被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Generative Adversarial Network (GAN) and its variants have recently attracted intensive research interests due to their elegant theoretical foundation and excellent empirical performance as generative models. These tools provide a promising direction in the studies where data availability is limited. One common issue in GANs is that the density of the learned generative distribution could concentrate on the training data points, meaning that they can easily remember training samples due to the high model complexity of deep networks. This becomes a major concern when GANs are applied to private or sensitive data such as patient medical records, and the concentration of distribution may divulge critical patient information. To address this issue, in this paper we propose a differentially private GAN (DPGAN) model, in which we achieve differential privacy in GANs by adding carefully designed noise to gradients during the learning procedure. We provide rigorous proof for the privacy guarantee, as well as comprehensive empirical evidence to support our analysis, where we demonstrate that our method can generate high quality data points at a reasonable privacy level.

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jaster · 2018-02

“Fun coincidence (or maybe not?), I just stumbled upon the following paper on arvix titled "Differentially Private Generative Adversarial Network" https://arxiv.org/pdf/1802.06739v1.pdf Its Related Work section also references some works on "differentially private learning in neural network". While the paper does not discuss directly OP remark about how …”

Differential Privacy for Dummies (2016)原评论 ↗
评论snowpid · 2023-01

“If the data is sparse, some researches used AI generated content to train another network. E.G. https://arxiv.org/pdf/1802.06739.pdf In some cases like here it also has privacy issues.”

The viral AI avatar app Lensa undressed me – without my consent原评论 ↗