Showing cs.CRShow all
3 papers · 1 filter
cs.CR2025
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
Christian Janos Lebeda, Matthew Regehr, Gautam Kamath +1
We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the pri…
cs.CR2025
Better Gaussian Mechanism using Correlated Noise
Christian Janos Lebeda
We present a simple variant of the Gaussian mechanism for answering differentially private queries when the sensitivity space has a certain common structure. Our motivating problem…
cs.CR2024
PLAN: Variance-Aware Private Mean Estimation
Martin Aumüller, Christian Janos Lebeda, Boel Nelson +1
Differentially private mean estimation is an important building block in privacy-preserving algorithms for data analysis and machine learning. Though the trade-off between privacy…