activity
20212026
most citedFine-Tuning Large Language Models with User-Level Differential Privacy

4 citations · 6 across the 7 of their papers we have counts for

collaborators
Showing 2024 · cs.CRShow all

1 paper · 2 filters

cs.CR2024

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms

Arun Ganesh

We give a procedure for computing group-level -DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implem…