Privacy auditing with one (1) training run

T Steinke, M Nasr, M Jagielski - Advances in Neural …, 2023 - proceedings.neurips.cc
We propose a scheme for auditing differentially private machine learning systems with a
single training run. This exploits the parallelism of being able to add or remove multiple …

Large language models can be strong differentially private learners

X Li, F Tramer, P Liang, T Hashimoto - ar**: Differentially private deep learning made easier and stronger
Z Bu, YX Wang, S Zha… - Advances in Neural …, 2023 - proceedings.neurips.cc
Per-example gradient clip** is a key algorithmic step that enables practical differential
private (DP) training for deep learning models. The choice of clip** threshold $ R …