Results 1 to 10 of about 2,499,134 (251)
Deep Learning with Differential Privacy [PDF]
Conference on Computer and Communications Security, 2016 Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information.
Martı́n Abadi +6 more
openalex +3 more sources
Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy
The Journal of Privacy and Confidentiality, 2021 We give a simple, computationally efficient, and node-differentially-private algorithm for estimating the parameter of an Erdos-Renyi graph---that is, estimating p in a G(n,p)---with near-optimal accuracy.
Adam Sealfon, Jonathan Ullman
doaj +3 more sources
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy [PDF]
Journal of Artificial Intelligence Research, 2023 Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and harder to reason about.
N. Ponomareva +8 more
semanticscholar +1 more source
Federated Learning of Gboard Language Models with Differential Privacy [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 We train and deploy language models (LMs) with federated learning (FL) and differential privacy (DP) in Google Keyboard (Gboard). The recent DP-Follow the Regularized Leader (DP-FTRL) algorithm is applied to achieve meaningfully formal DP guarantees ...
Zheng Xu +7 more
semanticscholar +1 more source
Review of Differential Privacy Research [PDF]
Jisuanji kexue, 2023 In the past decade,widespread data collection has become the norm.With the rapid development of large-scale data analysis and machine learning,data privacy is facing fundamental challenges.Exploring the trade-offs between privacy protection and data ...
ZHAO Yuqi, YANG Min
doaj +1 more source
What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy [PDF]
USENIX Security Symposium, 2023 Differential privacy (DP) is a mathematical privacy notion increasingly deployed across government and industry. With DP, privacy protections are probabilistic: they are bounded by the privacy budget parameter, $\epsilon$.
Priyanka Nanayakkara +4 more
semanticscholar +1 more source
Bounded and Unbiased Composite Differential Privacy [PDF]
IEEE Symposium on Security and Privacy, 2023 The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, traditional differentially private mechanisms tend to produce unbounded outputs
Kai Zhang +7 more
semanticscholar +1 more source
Numerical Composition of Differential Privacy [PDF]
Neural Information Processing Systems, 2021 We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of \emph{privacy loss random variables} to quantify the privacy loss of DP algorithms.The ...
Sivakanth Gopi, Y. Lee, Lukas Wutschitz
semanticscholar +1 more source
Privacy view and target of differential privacy
网络与信息安全学报, 2023 The study aimed to address the challenges in understanding the privacy goals of differential privacy by analyzing the privacy controversies surrounding it in various fields.It began with the example of data correlation and highlighted the differing ...
Jingyu JIA, Chang TAN, Zhewei LIU, Xinhao LI, Zheli LIU, Tao ZHANG
doaj +3 more sources
"I need a better description": An Investigation Into User Expectations For Differential Privacy
The Journal of Privacy and Confidentiality, 2023 Despite recent widespread deployment of differential privacy, relatively little is known about what users think of differential privacy. In this work, we seek to explore users' privacy expectations related to differential privacy.
Rachel Cummings +2 more
doaj +3 more sources