Equivariant Differentially Private Deep Learning: Why DP-SGD Needs
Sparser Models

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models

30 January 2023

Florian A. Hölzl

Daniel Rueckert

Georgios Kaissis

Papers citing "Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models"

5 / 5 papers shown

Title
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy Kristian Schwethelm Johannes Kaiser Jonas Kuntzer Mehmet Yigitsoy Daniel Rueckert Georgios Kaissis 27 0 0 01 Oct 2024
Not all noise is accounted equally: How differentially private learning benefits from large sampling rates Friedrich Dörmann Osvald Frisk L. Andersen Christian Fischer Pedersen FedML 44 25 0 12 Oct 2021
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning Da Yu Huishuai Zhang Wei Chen Tie-Yan Liu FedML SILM 91 110 0 25 Feb 2021
Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks Torsten Hoefler Dan Alistarh Tal Ben-Nun Nikoli Dryden Alexandra Peste MQ 136 679 0 31 Jan 2021
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 267 1,798 0 14 Dec 2020