Task-aware Kernel Stein certificates for Rényi differential privacy
Abstract
Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can be difficult to compute. In particular, Rènyi differential privacy guarantees that exploit task-specific information, as in Rènyi Pufferfish privacy, can be challenging. Here we use kernel Stein discrepancies based on escort distributions to provide certificates for Rènyi differential privacy. By designing the kernel to focus on the relevant privacy directions, we also derive task-aware privacy certificates. We provide exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms, with separate task-aware guarantees. A real data set example illustrates how the protected comparison set and the released subspace jointly determine the resulting certificates.
Related
- Conditional Kernel Stein Discrepancy
- Kernel-Checked Frontier Certificates for Erdős Problem 414
- Prophet Inequalities under Local Differential Privacy
- Performative Privacy: When Differential Privacy Maximizes Utility
- Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent
BibTeX
@misc{wirth2026taskaware,
title = {{Task-aware Kernel Stein certificates for Rényi differential privacy}},
author = {Leoni Carla Wirth and Tara Trauthwein and Gesine Reinert},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.23798},
eprint = {2610.23798},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.23798},
}
RIS
TY - UNPB
TI - Task-aware Kernel Stein certificates for Rényi differential privacy
AU - Leoni Carla Wirth
AU - Tara Trauthwein
AU - Gesine Reinert
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.23798
UR - https://arxiv.org/abs/2610.23798
AB - Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can be difficult to compute. In particular, Rènyi differential privacy guarantees that exploit task-specific information, as in Rènyi Pufferfish privacy, can be challenging. Here we use kernel Stein discrepancies based on escort distributions to provide certificates for Rènyi differential privacy. By designing the kernel to focus on the relevant privacy directions, we also derive task-aware privacy certificates. We provide exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms, with separate task-aware guarantees. A real data set example illustrates how the protected comparison set and the released subspace jointly determine the resulting certificates.
ER -