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…

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

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.

This paper lays the theoretical foundation for incorporating public data into differential privacy mechanisms for improved synthetic data generation.

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 optimizes the arrangement of codewords transmitted over a binary symmetric channel to improve differential privacy guarantees without increasing utility cost or real-time computational over…

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 introduces an attack, PRIVX, demonstrating that even differentially private (DP) Graph Neural Network (GNN) explanations leak enough structural information to allow an adversary to accurate…

The paper introduces SMA-DP-SGD, a Spectral Memory-Aware Differential Privacy method that enhances standard DP-SGD by incorporating a memory branch derived from past noisy updates, improving model uti…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

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 proposes a Jacobian-guided anisotropic noise reshaping technique to selectively attenuate noise in task-relevant subspaces, significantly enhancing data utility while maintaining Local Diffe…

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 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…

DDP-SA is a novel federated learning framework that combines local differential privacy and secure aggregation to achieve robust, scalable, and highly private model training.

This paper provides a comprehensive, practitioner-oriented framework and survey to guide the selection and evaluation of differentially private methods for releasing sensitive graph data.

The paper proposes DP-MacAdam, a novel differentially private optimization algorithm that simultaneously uses adaptive gradient clipping and momentum, achieving improved model accuracy over existing m…

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…