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…

This paper develops improved Gaussian mechanisms for Rényi Pufferfish Privacy (RPP) by incorporating Gaussian and Gaussian-mixture priors, significantly reducing the required noise and improving the p…

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

The paper demonstrates that by introducing carefully designed correlations among locally added noise variables, local differential privacy mechanisms can achieve an estimation cost matching the optima…

This paper addresses the challenging problem of multi-objective submodular maximization under a cardinality constraint while ensuring differential privacy, proposing novel algorithms with approximatio…

The paper introduces novel, efficient differentially private algorithms for estimating monotone statistics, significantly improving sample complexity compared to existing methods.

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 proposes DPSR-CG, a novel differentially private selective release mechanism that rigorously maintains strict privacy guarantees while significantly improving model utility compared to exist…

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…

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

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 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…

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 differentially private manifold denoising framework that allows noisy, non-private query points to be corrected using sensitive reference data while providing formal $(\varepsil…

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…

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…