.png){kind=icon}
返回
Differential Privacy for Tensor-Valued Queries
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2021.3089884.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Private individual information are increasingly exposed through high-dimensional and high-order data, with the wide deployment of learning techniques. These data are typically expressed in form of tensors, but there is no principled way to guarantee privacy for tensor-valued queries. Conventional differential privacy is typically applied to scalar values without a precise definition on the shape of the queried data. Realizing that the conventional mechanisms do not take the data structural information into account, we propose Tensor Variate Gaussian (TVG), a new (epsilon, delta)-differential privacy mechanism for tensor-valued queries. We further introduce two mechanisms based on TVG with an improved utility by imposing the unimodal differentially-private noise. With the utility space available, the proposed mechanisms can be instantiated with an optimized utility, and the optimization problem has a closed-form solution scalable to large-scale problems. Finally, we experimentally test our mechanisms on a variety of datasets and models, demonstrating that TVG is superior than other state-of-the-art mechanisms on tensor-valued queries.
Keyword:
Differential privacy
deep learning
stochastic gradient descent
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8
论文数:
5.3K
被引数:
2.3W
机构
引用论文
Identification of Small Molecules that Disrupt Signaling between ABL and Its Positive Regulator RIN1.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容