{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.16952",
  "author_total": 7,
  "authors": [
    {
      "name": "Kareem Amin"
    },
    {
      "name": "Rudrajit Das"
    },
    {
      "name": "Alessandro Epasto"
    },
    {
      "name": "Adel Javanmard"
    },
    {
      "name": "Dennis Kraft"
    },
    {
      "name": "Mónica Ribero"
    },
    {
      "name": "Sergei Vassilvitskii"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cvh1t4vvc8jpq.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.16952",
  "fulltext_url": null,
  "id": "cvh1t4vvc8jpq",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.16952",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Privacy-Preserving Technologies in Data"
    ]
  ],
  "openalex": "W7164889095",
  "pdf_url": "https://arxiv.org/pdf/2606.16952",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cvh1t4vvc8jpq.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T15:21:06Z",
      "native_id": "2606.16952",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.16952"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data",
  "title_text": "Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:31Z",
  "url": "https://research.draconitic.com/paper/cvh1t4vvc8jpq",
  "venue": "arXiv",
  "versions": []
}