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

The paper introduces a Gaussian Differential Privacy (GDP)-based auditing framework to provide the first tight audits of privacy guarantees for state-of-the-art synthetic data generators like MST and…

The paper introduces the PML envelope, a novel definition that provides a robust and operationally meaningful measure of information leakage about a secret, satisfying both post-processing robustness…

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 introduces CIPL, a unified channel-oriented framework, demonstrating that privacy leakage in LLM agents is governed by observable data channels and pipeline interactions, rather than being l…

This paper introduces a novel framework for differentially private sampling by using the Wasserstein distance as the utility measure, proposing the Wasserstein Projection Mechanism (WPM) to address li…

RootGuard introduces a dependency-aware privacy mechanism that sanitizes private data roots once, ensuring consistent privacy guarantees across multiple multi-turn agent interactions, significantly ou…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

The paper introduces Zero-Run privacy auditing, a post-hoc framework that allows for practical differential privacy evaluation of large, deployed models without requiring retraining or controlled data…

TADP-RME introduces a trust-adaptive differential privacy framework that enhances data system reliability by dynamically adjusting the privacy budget based on user trust and disrupting geometric struc…

The paper proposes a Quantitative Information Flow (QIF) framework to systematically and rigorously compare Local Differential Privacy (LDP) frequency estimation protocols, moving beyond simple $\vare…

The paper introduces LLM-CEG, an extended framework that uses membership inference attack success rates and model perplexity to systematically audit and optimize the privacy-utility trade-off when fin…

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 a new evaluation framework showing that, under realistic conditions, Membership Inference Attacks (MIAs) are weak privacy threats, suggesting that relying on them as a primary priva…

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 proposes PINA, a two-stage differentially private clustered federated learning framework that improves convergence and robustness by using low-rank adaptation and a normality-driven aggregat…

The paper introduces Bayesian Membership Privacy (BMP), a sampling-aware framework that accurately quantifies node-level membership privacy in Graph Neural Networks by treating graph sampling probabil…

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…

This paper demonstrates that standard privacy guarantees for multi-tenant RAG services fail when multiple accounts from the same tenant collude, proposing a novel audit protocol to quantify this joint…