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 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 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 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 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 proposes FedPower, a novel differentially private cross-silo Federated Learning framework that uses PowerDP to reconstruct and project client updates into a secure low-rank space, effectivel…

The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consu…

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…

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 provides a tight, transparent, and closed-form analysis of the trade-off function for Differentially Private SGD using random shuffling, significantly improving upon previous methods and est…

The paper proposes PAC-DP, a personalized adaptive clipping framework that dynamically adjusts gradient clipping thresholds based on the desired privacy budget, significantly improving the privacy-uti…

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.

The paper provides the first theoretical convergence analysis for machine learning training under fully homomorphic encryption combined with differential privacy, improving efficiency and scalability.

The paper proposes Byz-Clip21-SGD2M, a novel algorithm that achieves high-probability convergence guarantees for Federated Learning by integrating robust aggregation, double momentum, and clipping, re…

The paper proposes an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation a…

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 proposes a Public/Private Hybrid Head-VFL (PPHH-VFL) architecture that significantly accelerates secure time-series inference by splitting the model head into efficient public and secure pri…

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…