mlsanityData to 7 Oct 2026

On Utility and Privacy in Synthetic Genomic Data

arXiv 2102.03314 ↗First posted 5 Feb 2021q-bio.GN cs.AI cs.CRcited by 8

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

Abstract (arXiv)

The availability of genomic data is essential to progress in biomedical research, personalized medicine, etc. However, its extreme sensitivity makes it problematic, if not outright impossible, to publish or share it. As a result, several initiatives have been launched to experiment with synthetic genomic data, e.g., using generative models to learn the underlying distribution of the real data and generate artificial datasets that preserve its salient characteristics without exposing it. This paper provides the first evaluation of both utility and privacy protection of six state-of-the-art models for generating synthetic genomic data. We assess the performance of the synthetic data on several common tasks, such as allele population statistics and linkage disequilibrium. We then measure privacy through the lens of membership inference attacks, i.e., inferring whether a record was part of the training data. Our experiments show that no single approach to generate synthetic genomic data yields both high utility and strong privacy across the board. Also, the size and nature of the training dataset matter. Moreover, while some combinations of datasets and models produce synthetic data with distributions close to the real data, there often are target data points that are vulnerable to membership inference. Looking forward, our techniques can be used by practitioners to assess the risks of deploying synthetic genomic data in the wild and serve as a benchmark for future work.

Key facts. Cited by 8 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 23 of its 79 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

23 of 79 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Practical Blind Membership Inference Attack via Differential Comparisons5 Jan

Other references · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2017Renyi Differential Privacycited by 643
  6. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  7. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  8. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  9. 2018Differentially Private Generative Adversarial Networkcited by 235
  10. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  11. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  12. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
10 more
  1. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  2. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  3. 2020Differentially Private Synthetic Medical Data Generation using Convolutional GANscited by 52
  4. 2017Differentially Private Mixture of Generative Neural Networkscited by 39
  5. 2020CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Recordscited by 37
  6. 2017Generating and designing DNA with deep generative modelscited by 30
  7. 2020EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoderscited by 28
  8. 2019GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Modelscited by 10
  9. 2013A systematic comparison of supervised classifierscited by 7
  10. 2018Machine learning and genomics: precision medicine vs. patient privacycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 1; 2026: 1.

8 papers.

  1. 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 23
  2. 2024Can I trust my fake data -- A comprehensive quality assessment framework for synthetic tabular data in healthcarecited by 17
  3. 2024Systematic Assessment of Tabular Data Synthesiscited by 17
  4. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  5. 2025A Consensus Privacy Metrics Framework for Synthetic Datacited by 8
  6. 2023Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directionscited by 4
  7. 2026Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspectivecited by 1
  8. 2024A primer on synthetic health datacited by 0