activity
20202023
most citedTight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

3 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

Collaborative Learning From Distributed Data With Differentially Private Synthetic Twin Data

Lukas Prediger, Joonas Jälkö, Antti Honkela +1

Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible. We p…

cs.LG2021★ 1 cited

D3p -- A Python Package for Differentially-Private Probabilistic Programming

Lukas Prediger, Niki Loppi, Samuel Kaski +1

We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general appl…