The paper introduces task‑aware kernel Stein certificates for Rényi differential privacy, leveraging kernel Stein discrepancies based on escort distributions to provide privacy guarantees. By tailoring the kernel to focus on relevant privacy directions, the authors derive exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms, including task‑aware guarantees. A real‑world data example demonstrates how the protected comparison set and the released subspace jointly influence the resulting certificates.
arXiv:2606. 12733v2 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice.
arXiv:2508.04800v2 Announce Type: replace-cross Abstract: We introduce a novel privatization framework for high-dimensional controlled variable selection. Our framework enables rigorous False Discove...
arXiv:2606. 09582v1 Announce Type: new Abstract: Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning.
The paper presents a Gaussian approximation for the privacy loss distribution in differentially private stochastic gradient descent (DP‑SGD) when subsampling is used. It shows that, after truncating rare large losses, the privacy loss behaves like a Gaussian with the same mean and variance, up to a small shift that grows only logarithmically with the error tolerance. This leads to tighter variance‑based bounds for subsampled mechanisms, improving upon previous Renyi‑divergence analyses and explaining the effectiveness of the connect‑the‑dots method for random allocation sampling.
arXiv:2606. 17995v1 Announce Type: cross Abstract: We study the privacy of releasing posterior sample paths from a Gaussian process (GP) when the entire training set including covariates and responses is private.
arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.
arXiv:2607. 06320v1 Announce Type: cross Abstract: We present the dithered Gaussian mechanism, a novel alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the noise distribution itself.
arXiv:2610. 19573v1 Announce Type: cross Abstract: Differential Privacy (DP) provides a rigorous framework for quantifying privacy guarantees.
arXiv:2503. 10945v3 Announce Type: replace-cross Abstract: Current practices for reporting differential privacy (DP) guarantees for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture.
arXiv:2310. 19043v3 Announce Type: replace-cross Abstract: Recent years have witnessed growing concerns about the privacy of sensitive data.
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
arXiv:2511. 07270v4 Announce Type: replace-cross Abstract: In differential privacy, random noise is introduced to privatize summary statistics of a sensitive dataset before releasing them.