中文
相关论文

相关论文: DP-SGD vs PATE: Which Has Less Disparate Impact on…

200 篇论文

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

机器学习 · 计算机科学 2023-05-25 Geon Heo , Junseok Seo , Steven Euijong Whang

Synthetic data generation is a fundamental task for many data management and data science applications. Spatial data is of particular interest, and its sensitive nature often leads to privacy concerns. We introduce GeoPointGAN, a novel…

机器学习 · 计算机科学 2022-05-19 Teddy Cunningham , Konstantin Klemmer , Hongkai Wen , Hakan Ferhatosmanoglu

Despite remarkable performance in producing realistic samples, Generative Adversarial Networks (GANs) often produce low-quality samples near low-density regions of the data manifold, e.g., samples of minor groups. Many techniques have been…

机器学习 · 计算机科学 2021-10-28 Jinhee Lee , Haeri Kim , Youngkyu Hong , Hye Won Chung

Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only…

Synthetic data generation has emerged as a promising approach to address the challenges of using sensitive financial data in machine learning applications. By leveraging generative models, such as Generative Adversarial Networks (GANs) and…

机器学习 · 计算机科学 2025-10-31 James Meldrum , Basem Suleiman , Fethi Rabhi , Muhammad Johan Alibasa

Recently the Generative Adversarial Network has become a hot topic. Considering the application of GAN in multi-user environment, we propose Distributed-GAN. It enables multiple users to train with their own data locally and generates more…

机器学习 · 计算机科学 2019-11-20 Xiaoyu Wang , Ye Deng , Jinjun Wang

Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…

机器学习 · 计算机科学 2024-01-12 Alexey Kurakin , Natalia Ponomareva , Umar Syed , Liam MacDermed , Andreas Terzis

Despite the recency of their conception, Generative Adversarial Networks (GANs) constitute an extensively researched machine learning sub-field for the creation of synthetic data through deep generative modeling. GANs have consequently been…

网络与互联网体系结构 · 计算机科学 2021-05-11 Hojjat Navidan , Parisa Fard Moshiri , Mohammad Nabati , Reza Shahbazian , Seyed Ali Ghorashi , Vahid Shah-Mansouri , David Windridge

Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent…

密码学与安全 · 计算机科学 2022-12-15 Jie Fu , Zhili Chen , XinPeng Ling

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a security game in which an adversary infers whether a target record…

密码学与安全 · 计算机科学 2026-05-18 Wenhao Wang , Shujie Cui , Hui Cui , Xingliang Yuan

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for…

机器学习 · 计算机科学 2019-09-26 Bingzhe Wu , Shiwan Zhao , ChaoChao Chen , Haoyang Xu , Li Wang , Xiaolu Zhang , Guangyu Sun , Jun Zhou

Public data has been frequently used to improve the privacy-accuracy trade-off of differentially private machine learning, but prior work largely assumes that this data come from the same distribution as the private. In this work, we look…

计算机视觉与模式识别 · 计算机科学 2023-09-04 Ruihan Wu , Chuan Guo , Kamalika Chaudhuri

Although machine learning models trained on massive data have led to break-throughs in several areas, their deployment in privacy-sensitive domains remains limited due to restricted access to data. Generative models trained with privacy…

机器学习 · 计算机科学 2022-06-22 Tianshi Cao , Alex Bie , Arash Vahdat , Sanja Fidler , Karsten Kreis

Differential privacy (DP) provides a principled approach to synthesizing data (e.g., loads) from real-world power systems while limiting the exposure of sensitive information. However, adversaries may exploit synthetic data to calibrate…

系统与控制 · 电气工程与系统科学 2025-05-05 Shengyang Wu , Vladimir Dvorkin

In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related…

计算机视觉与模式识别 · 计算机科学 2018-11-02 Daniel Sáez Trigueros , Li Meng , Margaret Hartnett

Generative adversarial networks (GANs) are one of the greatest advances in AI in recent years. With their ability to directly learn the probability distribution of data, and then sample synthetic realistic data. Many applications have…

Generative adversarial networks (GANs) generate data based on minimizing a divergence between two distributions. The choice of that divergence is therefore critical. We argue that the divergence must take into account the hypothesis set and…

机器学习 · 计算机科学 2019-11-07 Ben Adlam , Corinna Cortes , Mehryar Mohri , Ningshan Zhang

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution. This paper presents, Tabular GAN (TGAN), a generative adversarial network which can generate…

机器学习 · 计算机科学 2018-11-29 Lei Xu , Kalyan Veeramachaneni

Synthetic data can be used in various applications, such as correcting bias datasets or replacing scarce original data for simulation purposes. Generative Adversarial Networks (GANs) are considered state-of-the-art for developing generative…

机器学习 · 计算机科学 2022-03-08 Gael Lederrey , Tim Hillel , Michel Bierlaire

Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in…

机器学习 · 计算机科学 2018-05-01 Daniel Jiwoong Im , He Ma , Graham Taylor , Kristin Branson