Minimax optimal procedures for locally private estimation

JC Duchi, MI Jordan, MJ Wainwright - Journal of the American …, 2018 - Taylor & Francis
Working under a model of privacy in which data remain private even from the statistician, we
study the tradeoff between privacy guarantees and the risk of the resulting statistical …

Privbayes: Private data release via bayesian networks

J Zhang, G Cormode, CM Procopiuc… - ACM Transactions on …, 2017 - dl.acm.org
Privacy-preserving data publishing is an important problem that has been the focus of
extensive study. The state-of-the-art solution for this problem is differential privacy, which …

Towards practical differential privacy for SQL queries

N Johnson, JP Near, D Song - Proceedings of the VLDB Endowment, 2018 - dl.acm.org
Differential privacy promises to enable general data analytics while protecting individual
privacy, but existing differential privacy mechanisms do not support the wide variety of …

Local privacy and statistical minimax rates

JC Duchi, MI Jordan… - 2013 IEEE 54th annual …, 2013 - ieeexplore.ieee.org
Working under local differential privacy-a model of privacy in which data remains private
even from the statistician or learner-we study the tradeoff between privacy guarantees and …

The complexity of differential privacy

S Vadhan - Tutorials on the Foundations of Cryptography …, 2017 - Springer
Differential privacy is a theoretical framework for ensuring the privacy of individual-level data
when performing statistical analysis of privacy-sensitive datasets. This tutorial provides an …

Adversarial machine learning

L Huang, AD Joseph, B Nelson… - Proceedings of the 4th …, 2011 - dl.acm.org
In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of
study: adversarial machine learning---the study of effective machine learning techniques …

Differential privacy and machine learning: a survey and review

Z Ji, ZC Lipton, C Elkan - arXiv preprint arXiv:1412.7584, 2014 - arxiv.org
The objective of machine learning is to extract useful information from data, while privacy is
preserved by concealing information. Thus it seems hard to reconcile these competing …

Functional mechanism: Regression analysis under differential privacy

J Zhang, Z Zhang, X Xiao, Y Yang… - arXiv preprint arXiv …, 2012 - arxiv.org
\epsilon-differential privacy is the state-of-the-art model for releasing sensitive information
while protecting privacy. Numerous methods have been proposed to enforce epsilon …

Differential privacy and robust statistics in high dimensions

X Liu, W Kong, S Oh - Conference on Learning Theory, 2022 - proceedings.mlr.press
We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …

Private convex empirical risk minimization and high-dimensional regression

D Kifer, A Smith, A Thakurta - Conference on Learning …, 2012 - proceedings.mlr.press
We consider\emphdifferentially private algorithms for convex empirical risk minimization
(ERM). Differential privacy (Dwork et al., 2006b) is a recently introduced notion of privacy …