Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data

• URL: http://arxiv.org/abs/2606.16952v1
• Date: Mon, 15 Jun 2026 16:54:02 GMT
• Title: Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data
• Abstract summary: We present a customizable empirical auditing framework designed to detect and explain data disclosures.<n>Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures"-where the system incidentally generates a user's data.
• Score: 56.86147283213652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information from the training corpus. In this work, we present a customizable empirical auditing framework designed to detect and explain such data disclosures. Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures''-where the system incidentally generates a user's data. By partitioning input data into training and holdout sets and applying rigorous statistical hypothesis testing, we determine if observed disclosures are consistent with strict privacy baselines, such as zero-learning or specific Differential Privacy (DP) bounds. Crucially, this approach requires no model access, no canary insertion, and no reference model training -only the synthetic output and a held-out control set. We demonstrate that this framework effectively functions as a membership inference attack, providing empirical lower bounds on privacy leakage that are tighter than prior data-based auditing methods. Our approach is model-agnostic, applies to any synthetic data generation mechanism, and requires orders of magnitude fewer computational resources than shadow-model or canary-based alternatives.

Related papers

• Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis [8.4361320391543]
  Tabular Generative Models are often argued to preserve privacy by creating synthetic datasets that resemble training data.<n>Membership Inference Attacks (MIAs) have recently emerged as a method for evaluating privacy leakage in synthetic data.<n>We propose a unified, model-agnostic threat framework that deploys a collection of attacks to estimate the maximum empirical privacy leakage in synthetic datasets.
  arXiv  Detail & Related papers  (2025-09-22T16:53:38Z)
• Managing Correlations in Data and Privacy Demand [4.855689194518906]
  We show that the standard HDP framework falls short when user data and privacy demands are allowed to be correlated.<n>We propose an alternate framework, Add-remove Heterogeneous Differential Privacy (AHDP), that jointly accounts for user data and privacy preference.
  arXiv  Detail & Related papers  (2025-09-02T22:03:13Z)
• Privacy Auditing Synthetic Data Release through Local Likelihood Attacks [7.780592134085148]
  Gene Likelihood Ratio Attack (Gen-LRA)<n>Gen-LRA formulates its attack by evaluating the influence a test observation has in a surrogate model's estimation of a local likelihood ratio over the synthetic data.<n>Results underscore Gen-LRA's effectiveness as a privacy auditing tool for the release of synthetic data.
  arXiv  Detail & Related papers  (2025-08-28T18:27:40Z)
• DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective [70.77570343385928]
  We introduce a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing)<n>We formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset.<n>Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery.<n>Our benchmark, DATABench, comprises 17 evasion attacks, 5 forgery attacks, and 9
  arXiv  Detail & Related papers  (2025-07-08T03:07:15Z)
• Simulation-based Bayesian Inference from Privacy Protected Data [0.0]
  We propose simulation-based inference methods from privacy-protected datasets.<n>We illustrate our methods on discrete time-series data under an infectious disease model and with ordinary linear regression models.
  arXiv  Detail & Related papers  (2023-10-19T14:34:17Z)
• Approximate, Adapt, Anonymize (3A): a Framework for Privacy Preserving Training Data Release for Machine Learning [3.29354893777827]
  We introduce a data release framework, 3A (Approximate, Adapt, Anonymize), to maximize data utility for machine learning. We present experimental evidence showing minimal discrepancy between performance metrics of models trained on real versus privatized datasets.
  arXiv  Detail & Related papers  (2023-07-04T18:37:11Z)
• 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)
• PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels [59.66777287810985]
  We introduce information-theoretic scores for privacy and utility, which quantify the average performance of an unfaithful user. We then theoretically characterize primitives in building families of encoding schemes that motivate the use of random deep neural networks.
  arXiv  Detail & Related papers  (2023-03-31T18:03:53Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)
• Representative & Fair Synthetic Data [68.8204255655161]
  We present a framework to incorporate fairness constraints into the self-supervised learning process. We generate a representative as well as fair version of the UCI Adult census data set. We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
  arXiv  Detail & Related papers  (2021-04-07T09:19:46Z)
• Federating Recommendations Using Differentially Private Prototypes [16.29544153550663]
  We propose a new federated approach to learning global and local private models for recommendation without collecting raw data. By requiring only two rounds of communication, we both reduce the communication costs and avoid the excessive privacy loss. We show local adaptation of the global model allows our method to outperform centralized matrix-factorization-based recommender system models.
  arXiv  Detail & Related papers  (2020-03-01T22:21:31Z)

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.