Subsampled rényi differential privacy and analytical moments accountant
We study the problem of subsampling in differential privacy (DP), a question that is the
centerpiece behind many successful differentially private machine learning algorithms …
centerpiece behind many successful differentially private machine learning algorithms …
Privacy amplification by subsampling: Tight analyses via couplings and divergences
Differential privacy comes equipped with multiple analytical tools for the design of private
data analyses. One important tool is the so-called" privacy amplification by subsampling" …
data analyses. One important tool is the so-called" privacy amplification by subsampling" …
The algorithmic foundations of differential privacy
The problem of privacy-preserving data analysis has a long history spanning multiple
disciplines. As electronic data about individuals becomes increasingly detailed, and as …
disciplines. As electronic data about individuals becomes increasingly detailed, and as …
Private empirical risk minimization: Efficient algorithms and tight error bounds
Convex empirical risk minimization is a basic tool in machine learning and statistics. We
provide new algorithms and matching lower bounds for differentially private convex …
provide new algorithms and matching lower bounds for differentially private convex …
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 …
when performing statistical analysis of privacy-sensitive datasets. This tutorial provides an …
Differentially private data publishing and analysis: A survey
Differential privacy is an essential and prevalent privacy model that has been widely
explored in recent decades. This survey provides a comprehensive and structured overview …
explored in recent decades. This survey provides a comprehensive and structured overview …
When is memorization of irrelevant training data necessary for high-accuracy learning?
Modern machine learning models are complex and frequently encode surprising amounts of
information about individual inputs. In extreme cases, complex models appear to memorize …
information about individual inputs. In extreme cases, complex models appear to memorize …
Generalization in adaptive data analysis and holdout reuse
Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to
understanding this problem focus on statistical inference and generalization of individual …
understanding this problem focus on statistical inference and generalization of individual …
A survey on differentially private machine learning
M Gong, Y Xie, K Pan, K Feng… - IEEE computational …, 2020 - ieeexplore.ieee.org
Recent years have witnessed remarkable successes of machine learning in various
applications. However, machine learning models suffer from a potential risk of leaking …
applications. However, machine learning models suffer from a potential risk of leaking …
Differentially private release and learning of threshold functions
We prove new upper and lower bounds on the sample complexity of (ε, δ) differentially
private algorithms for releasing approximate answers to threshold functions. A threshold …
private algorithms for releasing approximate answers to threshold functions. A threshold …