Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data | Paper Citation Record

Observation 1492e760-9254-47e8-8b11-2a791aa73014 · outbound

This paper cites Deep learning with differential privacy.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Deep learning with differential privacy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:47.423428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3e8805-6e13-4546-a043-5cbbdf4fe761 · outbound

This paper cites The us census bureau adopts differential privacy.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data The us census bureau adopts differential privacy

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:47.605633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 150f3762-6517-4377-adf2-6415f8a94960 · outbound

This paper cites Anonymous-by-construction: An llm-driven framework for privacy-preserving text.arXiv preprint arXiv:2603.17217, 2026.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Anonymous-by-construction: An llm-driven framework for privacy-preserving text.arXiv preprint arXiv:2603.17217, 2026

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:47.719059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4842e1dd-98ae-4288-8cc3-6b300f14daa5 · outbound

This paper cites Private prediction for large-scale synthetic text gener- ation.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Private prediction for large-scale synthetic text gener- ation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:47.856981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acc44fc6-45fc-461f-be2e-cc8dc18b37dd · outbound

This paper cites Reconstructing training data with informed adversaries.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Reconstructing training data with informed adversaries

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:47.962117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9cf0070-7f81-46f4-843c-fe04624f8457 · outbound

This paper cites Optimizing Canaries for Privacy Auditing with Metagradient Descent.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Optimizing Canaries for Privacy Auditing with Metagradient Descent

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.105239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e763c2-8e7d-4b41-a2ff-114ea2080fd0 · outbound

This paper cites Membership inference attacks from first principles.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Membership inference attacks from first principles

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.270033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bac4668-4c25-49f1-813d-dcc2f61c2ca6 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Quantifying Memorization Across Neural Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.430953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f8e5c9-d85a-46f9-9162-75e0d32ec93f · outbound

This paper cites The secret sharer: Evaluating and testing unintended memorization in neural networks.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data The secret sharer: Evaluating and testing unintended memorization in neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.519120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a413e642-3959-4775-94e3-f321ad2ebc5b · outbound

This paper cites Gan-leaks: A taxonomy of membership inference attacks against generative models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Gan-leaks: A taxonomy of membership inference attacks against generative models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.658689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35c362da-7251-4159-a739-9e7c8d39ef32 · outbound

This paper cites Calibrating noise to sensi- tivity in private data analysis.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Calibrating noise to sensi- tivity in private data analysis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.810330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec25e618-f304-4fd8-857c-f3271c8a99e6 · outbound

This paper cites Calibrating noise to sen- sitivity in private data analysis.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Calibrating noise to sen- sitivity in private data analysis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.907596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755ad7f0-178a-48c1-83e4-fd66f6d8d88e · outbound

This paper cites Differ- entially private optimization with sparse gradients.Advances in Neural Information Processing Systems, 37:63406–63440, 2024.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differ- entially private optimization with sparse gradients.Advances in Neural Information Processing Systems, 37:63406–63440, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.002200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de19083-07b6-4ae6-85d7-7fdad0db6e31 · outbound

This paper cites Property testing for differential privacy, 2019.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Property testing for differential privacy, 2019

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.116892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f894f1d-372e-423d-938c-2d9d41add35a · outbound

This paper cites Cloud Data Loss Prevention (Cloud DLP) api.https://docs.cloud.google.com/ sensitive-data-protection/docs/infotypes-reference, 2026.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Cloud Data Loss Prevention (Cloud DLP) api.https://docs.cloud.google.com/ sensitive-data-protection/docs/infotypes-reference, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.273936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ad301fa-7373-4b2d-8ce6-9693aebad2f5 · outbound

This paper cites Bounding train- ing data reconstruction in private (deep) learning.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Bounding train- ing data reconstruction in private (deep) learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.378561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d812ca25-b717-479a-80c4-40f660bd6960 · outbound

This paper cites The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.505084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51052b2a-b978-44f5-affe-a29569ff9379 · outbound

This paper cites Reconstruction and Membership Inference Attacks against Generative Models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Reconstruction and Membership Inference Attacks against Generative Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.572533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d53205d1-890b-48ed-a193-390d3f6f2ad1 · outbound

This paper cites Statistics and causal inference.Journal of the American Statistical Associa- tion, 81(396):945–960, 1986.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Statistics and causal inference.Journal of the American Statistical Associa- tion, 81(396):945–960, 1986

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.632050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f551d260-970d-4319-b0e9-809c0a69198f · outbound

This paper cites Auditing differentially private machine learning: How private is private SGD?Advances in Neural Information Processing Systems, 33:22205–22216, 2020.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Auditing differentially private machine learning: How private is private SGD?Advances in Neural Information Processing Systems, 33:22205–22216, 2020

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.718125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329f3565-70dc-4f51-8214-2a1cadd5899e · outbound

This paper cites Evaluating differentially private machine learning in practice.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Evaluating differentially private machine learning in practice

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.797851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6426826b-302c-4915-ace8-470f9334f7b9 · outbound

This paper cites Synthetic Data -- what, why and how?.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Synthetic Data -- what, why and how?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.868216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3086436-2a48-404f-8d08-41d4d39cecd5 · outbound

This paper cites The enron corpus: A new dataset for email classification research.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data The enron corpus: A new dataset for email classification research

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.910384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e47ef3-9cd3-43ba-8d5b-b50c9ce32a80 · outbound

This paper cites Linkedin job postings (2023 - 2024), 2024.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Linkedin job postings (2023 - 2024), 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:49.963194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88157295-aba4-449a-829f-e8b4d9a7e390 · outbound

This paper cites Harnessing large-language models to generate private synthetic text.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Harnessing large-language models to generate private synthetic text

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.068311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4034cf1c-1193-4292-b784-c097a09ef73d · outbound

This paper cites Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.140301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340961fc-3fd2-4e5d-b866-3feef06a813f · outbound

This paper cites Differentially Private Synthetic Data via Foundation Model APIs 1: Images.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.220869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 676897a0-47d3-4cb4-8693-dfc149788708 · outbound

This paper cites Differentially private language models for secure data sharing.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differentially private language models for secure data sharing

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.308477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3f52b9-56df-4b06-823c-d63776b72040 · outbound

This paper cites Mann-whitney u test.The Corsini encyclopedia of psychology, pages 1–1, 2010.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Mann-whitney u test.The Corsini encyclopedia of psychology, pages 1–1, 2010

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.368771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffee2b9-4cb1-4b50-a5d0-974c85e3c508 · outbound

This paper cites Achilles’ heels: vulnerable record identification in synthetic data publishing.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Achilles’ heels: vulnerable record identification in synthetic data publishing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.428566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9288e6ad-f692-4934-badb-c17dd25bcdac · outbound

This paper cites Copyright Traps for Large Language Models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Copyright Traps for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.473111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ccd5ce4-d555-4fcd-9f37-de7e9b353788 · outbound

This paper cites The canary’s echo: Auditing privacy risks of llm-generated synthetic text.arXiv preprint arXiv:2502.14921, 2025.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data The canary’s echo: Auditing privacy risks of llm-generated synthetic text.arXiv preprint arXiv:2502.14921, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.523343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d207183f-2e7c-472a-95fe-c3a1c8523e11 · outbound

This paper cites Tight auditing of differentially private machine learning.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Tight auditing of differentially private machine learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.602503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df7ac9e8-5092-41b7-8066-8af6c4fe3efb · outbound

This paper cites How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.687522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8e8c485-08ee-4f4c-a19f-c7345a71ba5f · outbound

This paper cites Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.773067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf6eb65-2130-44ae-9f02-8563a3ebb3de · outbound

This paper cites Differential privacy defenses and sampling attacks for membership inference.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differential privacy defenses and sampling attacks for membership inference

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.845377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1989c92-1121-458a-9a37-8406e84d9dab · outbound

This paper cites PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.898244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc54bca3-287b-441b-8bfa-5f310000a015 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Detecting Pretraining Data from Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:50.956012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5fe208-0653-438b-bbf5-9b0707f563f3 · outbound

This paper cites Membership inference attacks against machine learning models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Membership inference attacks against machine learning models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.037822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf5ea022-72dc-4bc9-88dc-83776e5fb5b0 · outbound

This paper cites Privacy auditing with one (1) training run.Advances in Neural Information Processing Systems, 36:49268–49280, 2023.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Privacy auditing with one (1) training run.Advances in Neural Information Processing Systems, 36:49268–49280, 2023

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.161859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49deb2bc-3911-4d15-a927-c9a4401aeeaf · outbound

This paper cites Privacy-preserving in-context learning with differentially private few-shot generation.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Privacy-preserving in-context learning with differentially private few-shot generation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.253748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd76521-b598-43ae-827c-92ef85617de4 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Gemma: Open Models Based on Gemini Research and Technology

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.338272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7dac700-ab63-4daf-9593-4cf44d0761af · outbound

This paper cites Proving membership in llm pretraining data via data watermarks.arXiv e-prints, pages arXiv–2402, 2024.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Proving membership in llm pretraining data via data watermarks.arXiv e-prints, pages arXiv–2402, 2024

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.421185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13860fe2-c197-4c98-9208-2ac0b4eda4d6 · outbound

This paper cites Synthetic-PII-Financial-Documents-North-America: A synthetic dataset for training language models to label and detect pii in domain specific formats, June 2024.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Synthetic-PII-Financial-Documents-North-America: A synthetic dataset for training language models to label and detect pii in domain specific formats, June 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.494470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ef001c-dcc9-419e-8b43-3755c7ab3008 · outbound

This paper cites Differentially pri- vate synthetic data via foundation model apis 2: Text.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Differentially pri- vate synthetic data via foundation model apis 2: Text

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.587255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d55466b4-f716-459d-ba97-07b728ff68ec · outbound

This paper cites Enhanced membership inference attacks against machine learning models.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Enhanced membership inference attacks against machine learning models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.658726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6fb5db8-b98d-4d8d-82cb-cc95a1c2055d · outbound

This paper cites Synthetic text generation with differential privacy: A simple and practical recipe.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Synthetic text generation with differential privacy: A simple and practical recipe

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.727318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c57d32-0c4f-497d-9c16-f45b35428cb1 · outbound

This paper cites Low-Cost High-Power Membership Inference Attacks.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Low-Cost High-Power Membership Inference Attacks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:51.779883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers