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…

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 investigates the vulnerability of Graph Neural Networks (GNNs) protected by Local Differential Privacy (LDP) to adversarial attacks, analyzing the interplay between privacy guarantees and a…

The paper presents the first general mechanism for counting arbitrary acyclic graph patterns under Local Differential Privacy (LDP), addressing challenges in pattern construction and node duplication.

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

The paper introduces local private information retrieval (local PIR), redefining user privacy in graph-replicated systems to focus on hiding the message index from servers, and demonstrates that local…

This paper investigates the privacy risks of inferring sensitive user attributes from Knowledge Graph Embeddings (KGEs) and proposes post-processing sanitization techniques to mitigate these risks.

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 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 using Differentially Private (DP) synthetic data, specifically through tabular synthesis and DP-Seeded Agent-Based Modeling (ABM), to resolve the conflict between data utility and p…

This paper generalizes the definition of privacy in graph-replicated Private Information Retrieval (PIR) by allowing each server to have an arbitrary, specific set of message indices it must keep priv…

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 DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…

The paper proposes FERMI, a method that significantly improves membership inference attacks against tabular diffusion models by leveraging auxiliary relational information available during training, e…

The paper proposes EPDQ, a tensor-based scheme that efficiently and privately computes exact shortest distance queries on large-scale encrypted graphs by combining specialized indexing and tensor repr…

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 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…