Cover Image

The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ganev, Georgi, Annamalai, Meenatchi Sundaram Muthu Selva, Mahiou, Sofiane, De Cristofaro, Emiliano
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy
by: Ganev, Georgi, et al.
Published: (2025)

"What do you want from theory alone?" Experimenting with Tight Auditing of Differentially Private Synthetic Data Generation
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging
by: Ganev, Georgi, et al.
Published: (2024)

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Tight Auditing of Differential Privacy in MST and AIM
by: Ganev, Georgi, et al.
Published: (2026)

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2025)

CLIOPATRA: Extracting Private Information from LLM Insights
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2026)

Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
by: Ganev, Georgi, et al.
Published: (2023)

It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
by: Annamalai, Meenatchi Sundaram Muthu Selva
Published: (2024)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2023)

Beyond the Crawl: Unmasking Browser Fingerprinting in Real User Interactions
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2025)

Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective
by: Ganev, Georgi, et al.
Published: (2026)

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
by: Ganev, Georgi, et al.
Published: (2023)

dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generation
by: Mahiou, Sofiane, et al.
Published: (2025)

A Unified Framework for Adversary-Aware Differential Privacy Bounds
by: Swanberg, Marika, et al.
Published: (2025)

Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance
by: Ganev, Georgi
Published: (2024)

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
by: Yao, Zexi, et al.
Published: (2025)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
by: Ganev, Georgi, et al.
Published: (2025)

End to End Collaborative Synthetic Data Generation
by: Pentyala, Sikha, et al.
Published: (2024)

Synthetic Data: Methods, Use Cases, and Risks
by: De Cristofaro, Emiliano
Published: (2023)

A Systematic Review of Federated Generative Models
by: Gargary, Ashkan Vedadi, et al.
Published: (2024)

Differentially Private Synthetic Data Generation for Relational Databases
by: Alimohammadi, Kaveh, et al.
Published: (2024)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
by: Wei, Jianxin, et al.
Published: (2022)

Differentially Private Synthetic Data Release for Topics API Outputs
by: Dick, Travis, et al.
Published: (2025)

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
by: Zhou, Yvonne, et al.
Published: (2024)

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
by: Gong, Chen, et al.
Published: (2025)

Differentially Private Synthetic Data Generation Using Context-Aware GANs
by: Kotal, Anantaa, et al.
Published: (2025)

Reveal-or-Obscure: A Differentially Private Sampling Algorithm for Discrete Distributions
by: Tasnim, Naima, et al.
Published: (2025)

End-to-End Anti-Backdoor Learning on Images and Time Series
by: Jiang, Yujing, et al.
Published: (2024)

Navigating the Deep: End-to-End Extraction on Deep Neural Networks
by: Liu, Haolin, et al.
Published: (2025)

The Discrete Gaussian for Differential Privacy
by: Canonne, Clément L., et al.
Published: (2020)

An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
by: Ghosh, Kushankur, et al.
Published: (2026)

An Adaptive End-to-End IoT Security Framework Using Explainable AI and LLMs
by: Baral, Sudipto, et al.
Published: (2024)

Oracle-Efficient Differentially Private Learning with Public Data
by: Block, Adam, et al.
Published: (2024)

LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples
by: Wu, Huiyu, et al.
Published: (2024)

Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation
by: Maddock, Samuel, et al.
Published: (2025)

Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
by: Swanberg, Marika, et al.
Published: (2025)

Differentially Private Synthetic Data with Private Density Estimation
by: Bojkovic, Nikolija, et al.
Published: (2024)

Differentially Private Knowledge Distillation via Synthetic Text Generation
by: Flemings, James, et al.
Published: (2024)