Evaluating Differentially Private Generation of Domain-Specific Text

• URL: http://arxiv.org/abs/2508.20452v1
• Date: Thu, 28 Aug 2025 05:57:47 GMT
• Title: Evaluating Differentially Private Generation of Domain-Specific Text
• Authors: Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Iqra Zahid, Yuping Wu, Warren Del-Pinto, Goran Nenadic, Siew-Kei Lam, Jie Zhang, Anil A Bharath,
• Abstract summary: We introduce a unified benchmark to systematically evaluate the utility and fidelity of text datasets generated under Differential Privacy guarantees.<n>We assess state-of-the-art privacy-preserving generation methods across five domain-specific datasets.
• Score: 33.72321050465059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To address this, differentially private synthetic data generation has emerged as a promising alternative. In this work, we introduce a unified benchmark to systematically evaluate the utility and fidelity of text datasets generated under formal Differential Privacy (DP) guarantees. Our benchmark addresses key challenges in domain-specific benchmarking, including choice of representative data and realistic privacy budgets, accounting for pre-training and a variety of evaluation metrics. We assess state-of-the-art privacy-preserving generation methods across five domain-specific datasets, revealing significant utility and fidelity degradation compared to real data, especially under strict privacy constraints. These findings underscore the limitations of current approaches, outline the need for advanced privacy-preserving data sharing methods and set a precedent regarding their evaluation in realistic scenarios.

Related papers

• Challenges in Enabling Private Data Valuation [17.450381366291754]
  Data valuation methods quantify how individual training examples contribute to a model's behavior.<n> valuation scores can reveal whether a person's data was included in training, whether it was unusually influential, or what sensitive patterns exist in proprietary datasets.<n>Privacy is fundamentally in tension with valuation utility under differential privacy (DP)
  arXiv  Detail & Related papers  (2026-02-27T22:21:14Z)
• PRIVET: Privacy Metric Based on Extreme Value Theory [8.447463478355845]
  Deep generative models are often trained on sensitive data, such as genetic sequences, health data, or more broadly, any copyrighted, licensed or protected content.<n>This raises critical concerns around privacy-preserving synthetic data, and more specifically around privacy leakage.<n>We propose PRIVET, a generic sample-based, modality-agnostic algorithm that assigns an individual privacy leak score to each synthetic sample.
  arXiv  Detail & Related papers  (2025-10-28T09:42:03Z)
• SynBench: A Benchmark for Differentially Private Text Generation [35.908455649647784]
  Data-driven decision support in high-stakes domains like healthcare and finance faces significant barriers to data sharing.<n>Recent generative AI models, such as large language models, have shown impressive performance in open-domain tasks.<n>But their adoption in sensitive environments remains limited by unpredictable behaviors and insufficient privacy-preserving datasets.
  arXiv  Detail & Related papers  (2025-09-18T03:57:50Z)
• Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead [7.410975558116122]
  Privacy-preserving synthetic data offers a promising solution to harness segregated data in high-stakes domains.<n>This survey presents the theoretical foundations of generative models and differential privacy followed by a review of state-of-the-art methods.<n>Our findings highlight key challenges including unaccounted privacy leakage, insufficient empirical verification of formal guarantees, and a critical deficit of realistic benchmarks.
  arXiv  Detail & Related papers  (2025-03-26T16:06:33Z)
• An applied Perspective: Estimating the Differential Identifiability Risk of an Exemplary SOEP Data Set [2.66269503676104]
  We show how to compute the risk metric efficiently for a set of basic statistical queries. Our empirical analysis based on an extensive, real-world scientific data set expands the knowledge on how to compute risks under realistic conditions.
  arXiv  Detail & Related papers  (2024-07-04T17:50:55Z)
• Collection, usage and privacy of mobility data in the enterprise and public administrations [55.2480439325792]
  Security measures such as anonymization are needed to protect individuals' privacy. Within our study, we conducted expert interviews to gain insights into practices in the field. We survey privacy-enhancing methods in use, which generally do not comply with state-of-the-art standards of differential privacy.
  arXiv  Detail & Related papers  (2024-07-04T08:29:27Z)
• A Summary of Privacy-Preserving Data Publishing in the Local Setting [0.6749750044497732]
  Statistical Disclosure Control aims to minimize the risk of exposing confidential information by de-identifying it. We outline the current privacy-preserving techniques employed in microdata de-identification, delve into privacy measures tailored for various disclosure scenarios, and assess metrics for information loss and predictive performance.
  arXiv  Detail & Related papers  (2023-12-19T04:23:23Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• A Unified View of Differentially Private Deep Generative Modeling [60.72161965018005]
  Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
  arXiv  Detail & Related papers  (2023-09-27T14:38:16Z)
• Auditing and Generating Synthetic Data with Controllable Trust Trade-offs [54.262044436203965]
  We introduce a holistic auditing framework that comprehensively evaluates synthetic datasets and AI models. It focuses on preventing bias and discrimination, ensures fidelity to the source data, assesses utility, robustness, and privacy preservation. We demonstrate the framework's effectiveness by auditing various generative models across diverse use cases.
  arXiv  Detail & Related papers  (2023-04-21T09:03:18Z)
• Private Set Generation with Discriminative Information [63.851085173614]
  Differentially private data generation is a promising solution to the data privacy challenge. Existing private generative models are struggling with the utility of synthetic samples. We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-07T10:02:55Z)
• Private Domain Adaptation from a Public Source [48.83724068578305]
  We design differentially private discrepancy-based algorithms for adaptation from a source domain with public labeled data to a target domain with unlabeled private data. Our solutions are based on private variants of Frank-Wolfe and Mirror-Descent algorithms.
  arXiv  Detail & Related papers  (2022-08-12T06:52:55Z)
• Data-driven Regularized Inference Privacy [33.71757542373714]
  We propose a data-driven inference privacy preserving framework to sanitize data. We develop an inference privacy framework based on the variational method. We present empirical methods to estimate the privacy metric.
  arXiv  Detail & Related papers  (2020-10-10T08:42:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.