mlsanityData to 7 Oct 2026

Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data

arXiv 2307.01701 ↗First posted 4 Jul 2023cs.CR cs.AIcited by 18

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the privacy of synthetic data, they currently assume the attacker to have access to an auxiliary dataset sampled from a similar distribution as the training dataset. This is often seen as a very strong assumption in practice, especially as the proposed main use cases for synthetic tabular data (e.g. medical data, financial transactions) are very specific and don't have any reference datasets directly available. We here show how this assumption can be removed, allowing for MIAs to be performed using only the synthetic data. Specifically, we developed three different scenarios: (S1) Black-box access to the generator, (S2) only access to the released synthetic dataset and (S3) a theoretical setup as upper bound for the attack performance using only synthetic data. Our results show that MIAs are still successful, across two real-world datasets and two synthetic data generators. These results show how the strong hypothesis made when auditing synthetic data releases - access to an auxiliary dataset - can be relaxed, making the attacks more realistic in practice.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 13 of its 34 references that are in the map. First posted on arXiv 4 Jul 2023.

Builds on

13 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Membership Inference Attacks From First Principles7 Dec

Other references · 12

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2019Modeling Tabular data using Conditional GANcited by 695
  3. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  4. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 105
  5. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  6. 2022TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Datacited by 56
  7. 2022A Unified Framework for Quantifying Privacy Risk in Synthetic Datacited by 45
  8. 2023Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishingcited by 28
  9. 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 23
  10. 2022Understanding Real-world Threats to Deep Learning Models in Android Appscited by 15
  11. 2021Correlation inference attacks against machine learning modelscited by 7
  12. 2020Design of a Privacy-Preserving Data Platform for Collaboration Against Human Traffickingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 6; 2026: 7.

18 papers.

Sort:

By area:

  1. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  2. 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Datacited by 11
  3. 2024Privacy Vulnerabilities in Marginals-based Synthetic Datacited by 10
  4. 2025Evaluating Differentially Private Generation of Domain-Specific Textcited by 5
  5. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  6. 2025MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Datacited by 4
  7. 2024A Zero Auxiliary Knowledge Membership Inference Attack on Aggregate Location Datacited by 3
  8. 2025Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detectioncited by 3
  9. 2024VFLGAN: Vertical Federated Learning-based Generative Adversarial Network for Vertically Partitioned Data Publicationcited by 1
  10. 2025Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Modelscited by 1
  11. 2026Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspectivecited by 1
  12. 2026A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilitiescited by 1
6 more
  1. 2024Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Modelscited by 0
  2. 2026Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimatorscited by 0
  3. 2026Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agentscited by 0
  4. 2026diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectoriescited by 0
  5. 2026ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generatorscited by 0
  6. 2026It does what it says on the tin: safe synthetic data from coarsened marginscited by 0