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 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…

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

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a light…

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 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 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, practical upper bound to estimate the worst-case performance of medical prediction models on the target population, even when the selection bias mechanism and target data a…

This paper empirically evaluates the effectiveness of Differential Privacy (DP) against Membership Inference Attacks (MIAs) in Federated Learning, demonstrating that a stacking attack strategy can det…

The paper proposes a novel two-stage framework to differentially privatize tables of counts by focusing on preserving the accuracy of the underlying count distribution, introducing the specialized cyc…

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…

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 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 proposes a three-step differentially private pipeline to simulate disease spread on sensitive contact networks, demonstrating that the added noise for privacy is generally small relative to…

The paper characterizes the optimal achievable rate for differentially private hypothesis testing using e-values, providing an exact algorithm for both fixed and sequential settings.

The paper introduces the Generalized Thresholding Mechanism (GTM) to solve the generalized private testing problem in differential privacy, achieving near-optimal accuracy and sample complexity guaran…