The paper introduces the $\alpha$-Wasserstein mechanism to achieve Rényi Pufferfish Privacy using Laplace and Gaussian noise, demonstrating that it generalizes existing privacy frameworks and reduces…

The paper introduces 'mixture mechanisms,' a novel class of additive noise mechanisms that achieve approximate differential privacy by mixing multiple Gaussian distributions, resulting in lower noise…

The paper introduces 'mixture mechanisms,' a novel class of additive noise mechanisms that achieve differential privacy for real-valued queries, significantly reducing noise compared to the standard G…

The paper introduces an optimal black-box auditing framework using Donsker-Varadhan estimators to estimate Rényi differential privacy (RDP) guarantees for machine learning algorithms.

This paper introduces a novel framework for differentially private sampling by using the Wasserstein distance as the utility measure, proposing the Wasserstein Projection Mechanism (WPM) to address li…

This paper corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.

The paper develops a unified theoretical framework to systematically characterize the optimal privacy-utility trade-off (PUT) and optimal Local Differential Privacy (LDP) channels for general statisti…

The paper develops a general framework to exactly characterize the composition of mechanisms satisfying multiple differential privacy constraints, extending known results to arbitrary numbers of const…

The paper derives new informational inequalities using Stam-like, moment-entropy-like inequalities, and a recently established Rényi entropy-based inequality. It obtains a Stam-like inequality connect…

The paper introduces Metric-Normalized Posterior Leakage (mPL), an attacker-aligned measure that provides a practical, certifiable privacy guarantee for machine learning systems consumed under joint o…

The paper introduces Fractional-Order Differentially Private Stochastic Gradient Descent (FO-DP-SGD), a mechanism that incorporates fractional memory into the gradient release process to improve priva…

This paper demonstrates that the classical discrete Laplace mechanism can be post-processed to create versatile, unbiased estimators for various subexponential functions, making it a preferred choice…

The paper introduces a novel realization-level privacy filtering approach that improves utility in differentially private data release by accounting for actual leakage rather than worst-case per-round…

The paper characterizes the minimax optimal excess-risk rate for pure $\varepsilon$-DP stochastic convex optimization with heavy-tailed gradients, providing an algorithm that achieves this rate.

The paper proposes IntraShuffler, a novel privacy-preserving middleware defense that enables gradient shuffling in Heterogeneous Differential Privacy Federated Learning (HDP-FL) systems, significantly…

The paper proposes IntraShuffler, a novel privacy-preserving middleware defense that enables gradient shuffling in Heterogeneous Differential Privacy Federated Learning (HDP-FL) while maintaining the…

The paper introduces Balanced Iteration Subsampling (BIS), a structured sampling scheme that is proven to achieve stronger privacy amplification than the standard Poisson subsampling used in DP-SGD by…

The paper proposes a novel exponential mechanism using quadratic approximations to fine-tune machine learning models on sensitive data while providing strong differential privacy guarantees.

This paper analyzes the Bayesian fixed-budget best-arm identification problem with abstention, showing that it induces a phase transition from polynomial to exponential decay of error probability.

This paper develops a perturbation theory for spherical Hellinger-Kantorovich (SHK) gradient flows, providing explicit, time-dependent bounds on divergence metrics to guarantee differential privacy fo…