The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

The paper quantifies the cost of privacy in language identification and generation using differentially private (DP) methods, finding that the cost is surprisingly mild, particularly absent under appr…

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper proposes a novel method to automatically enforce differential privacy in stream-based runtime monitoring specifications by analyzing temporal dependencies and injecting calibrated noise.

The paper proposes PPRoute, a privacy-preserving LLM routing framework that significantly speeds up secure model selection while maintaining high performance comparable to non-private methods.

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 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 the first general defense framework to make all union-preserving Differential Privacy (DP) protocols, specifically those based on shuffle-DP, resilient against poisoning attacks.

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…

TAPAS introduces an efficient, asymmetric two-server private aggregation scheme that significantly reduces computational and communication costs for large-scale federated learning compared to existing…

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 proposes Context-aware Metric Differential Privacy (C-mDP), a framework that improves vehicle location privacy by modeling temporal dependencies, achieving higher data utility than standard…

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 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 introduces public-decay Homomorphic State Space Models (HSSMs) that enable efficient, high-accuracy sequence inference directly on encrypted data, significantly outperforming existing encryp…

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.

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

The paper introduces PolyVeil, a protocol for private Boolean summation that uses permutation matrices in the Birkhoff polytope, achieving strong security guarantees while highlighting a fundamental t…

The paper introduces a mathematical and cryptographic framework for exactly recovering a single, noisy, high-dimensional discrete path from aggregated and incomplete observable data.