1 code implementation • 14 Jun 2023 • Martin Aumüller, Christian Janos Lebeda, Boel Nelson, Rasmus Pagh
Under a concentration assumption on $\mathcal{D}$, we show how to exploit skew in the vector $\boldsymbol{\sigma}$, obtaining a (zero-concentrated) differentially private mean estimate with $\ell_2$ error proportional to $\|\boldsymbol{\sigma}\|_1$.
no code implementations • 8 Mar 2021 • Boel Nelson
To fill the gap in the literature, we propose a novel application of factor experiments to create data aware error predictions.
Cryptography and Security
no code implementations • 27 Jan 2021 • Boel Nelson
Motivated by the lack of tools to gather poll data under differential privacy, we set out to engineer our own tool.
Cryptography and Security