paper-with-me

홈 › Papers

Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead

2025-03-26 · Viktor Schlegel, Anil A Bharath, Zilong Zhao, Kevin Yee

Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains where information is compartmentalized for regulatory, privacy, or institutional reasons. This survey provides a comprehensive framework for understanding the landscape of privacy-preserving synthetic data, presenting the theoretical foundations of generative models and differential privacy followed by a review of state-of-the-art methods across tabular data, images, and text. Our synthesis of evaluation approaches highlights the fundamental trade-off between utility for down-stream tasks and privacy guarantees, while identifying critical research gaps: the lack of realistic benchmarks representing specialized domains and insufficient empirical evaluations required to contextualise formal guarantees. Through empirical analysis of four leading methods on five real-world datasets from specialized domains, we demonstrate significant performance degradation under realistic privacy constraints ($\epsilon \leq 4$), revealing a substantial gap between results reported on general domain benchmarks and performance on domain-specific data. %Our findings highlight key challenges including unaccounted privacy leakage, insufficient empirical verification of formal guarantees, and a critical deficit of realistic benchmarks. These challenges underscore the need for robust evaluation frameworks, standardized benchmarks for specialized domains, and improved techniques to address the unique requirements of privacy-sensitive fields such that this technology can deliver on its considerable potential.

📄 PDF Abstract BibTeX arXiv:2503.20846

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

2023-03-02 · NeurIPS 2023 11

We focus on the problem of generating high-quality, private synthetic glucose traces, a task generalizable to many other time series sources. Existing methods for time series data synthesis, such as those using Generativ…

Privacy PreservingTime Series

Privacy Amplification Persists under Unlimited Synthetic Data Release

2026-02-03 · Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard arxiv

We study privacy amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work b…

Synthetic Data Generation and Differential Privacy using Tensor Networks' Matrix Product States (MPS)

2025-08-08 · Alejandro Moreno R., Desale Fentaw, Samuel Palmer, Raúl Salles de Padua 외 arxiv

Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a metho…

Synthetic Data Generation

PATE-TabTransGAN: Differentially Private Synthetic Tabular Data Generation via Transformer-Based Student Discrimination

2026-05-26 · M. Youssef, M. Woźniak arxiv

Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theoretical protection typically sacrifice the modeling of inter-feature…

Tabular Data Generation

PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees

2019-05-01 · ICLR 2019 5 · Jinsung Yoon, James Jordon, Mihaela van der Schaar

Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sh…

BIG-bench Machine LearningSynthetic Data Generation