9 papers
Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy
Nikita P. Kalinin, Rasmus Pagh
We present the dithered Gaussian mechanism, a novel alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the nois…
DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training
Nikita P. Kalinin, Ryan McKenna, Rasmus Pagh +1
Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential privacy guarantees. Several recent ex…
Privacy by Postprocessing the Discrete Laplace Mechanism
Quentin Hillebrand, Jacob Imola, Rasmus Pagh +1
We show that an "old dog", the classical discrete Laplace (aka.~geometric) mechanism, can "perform new tricks": 1. It can be post-processed to yield a simple, unbiased estimator of…
Differentially Private Quantiles with Smaller Error
Jacob Imola, Fabrizio Boninsegna, Hannah Keller +3
In the approximate quantiles problem, the goal is to output quantile estimates, the ranks of which are as close as possible to given quantiles $0 \leq q_1 \leq\dots \leq q_…
Piquant: Private Quantile Estimation in the Two-Server Model
Hannah Keller, Jacob Imola, Fabrizio Boninsegna +2
Quantiles are key in distributed analytics, but computing them over sensitive data risks privacy. Local differential privacy (LDP) offers strong protection but lower accuracy than…
Private Lossless Multiple Release
Joel Daniel Andersson, Lukas Retschmeier, Boel Nelson +1
Koufogiannis et al. (2016) showed a result for Laplace noise-based differentially private mechanisms: given an -DP release, a new release wi…