Dp-cryptography: marrying differential privacy and cryptography in emerging applications

S Wagh, X He, A Machanavajjhala… - Communications of the …, 2021 - dl.acm.org
DP-cryptography: marrying differential privacy and cryptography in emerging applications
Page 1 84 COMMUNICATIONS OF THE ACM | FEBRUARY 2021 | VOL. 64 | NO. 2 review …

Winning the NIST Contest: A scalable and general approach to differentially private synthetic data

R McKenna, G Miklau, D Sheldon - arxiv preprint arxiv:2108.04978, 2021 - arxiv.org
We propose a general approach for differentially private synthetic data generation, that
consists of three steps:(1) select a collection of low-dimensional marginals,(2) measure …

(Amplified) Banded Matrix Factorization: A unified approach to private training

CA Choquette-Choo, A Ganesh… - Advances in …, 2024 - proceedings.neurips.cc
Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially
improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in a …

Tabular and latent space synthetic data generation: a literature review

J Fonseca, F Bacao - Journal of Big Data, 2023 - Springer
The generation of synthetic data can be used for anonymization, regularization,
oversampling, semi-supervised learning, self-supervised learning, and several other tasks …

Improved differential privacy for sgd via optimal private linear operators on adaptive streams

S Denisov, HB McMahan, J Rush… - Advances in …, 2022 - proceedings.neurips.cc
Motivated by recent applications requiring differential privacy in the setting of adaptive
streams, we investigate the question of optimal instantiations of the matrix mechanism in this …

Differentially private query release through adaptive projection

S Aydore, W Brown, M Kearns… - International …, 2021 - proceedings.mlr.press
We propose, implement, and evaluate a new algo-rithm for releasing answers to very large
numbersof statistical queries likek-way marginals, sub-ject to differential privacy. Our …

Graphical-model based estimation and inference for differential privacy

R McKenna, D Sheldon… - … Conference on Machine …, 2019 - proceedings.mlr.press
Many privacy mechanisms reveal high-level information about a data distribution through
noisy measurements. It is common to use this information to estimate the answers to new …

Aim: An adaptive and iterative mechanism for differentially private synthetic data

R McKenna, B Mullins, D Sheldon, G Miklau - arxiv preprint arxiv …, 2022 - arxiv.org
We propose AIM, a novel algorithm for differentially private synthetic data generation.\aim is
a workload-adaptive algorithm, within the paradigm of algorithms that first selects a set of …

Privatesql: a differentially private sql query engine

I Kotsogiannis, Y Tao, X He, M Fanaeepour… - Proceedings of the …, 2019 - dl.acm.org
Differential privacy is considered a de facto standard for private data analysis. However, the
definition and much of the supporting literature applies to flat tables. While there exist …

Leveraging public data for practical private query release

T Liu, G Vietri, T Steinke, J Ullman… - … on Machine Learning, 2021 - proceedings.mlr.press
In many statistical problems, incorporating priors can significantly improve performance.
However, the use of prior knowledge in differentially private query release has remained …