# On Utility and Privacy in Synthetic Genomic Data

arXiv: https://arxiv.org/abs/2102.03314 · HTML: https://mlsanity.com/paper/2102.03314/

## Key facts

- Cited by 8 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [White-box vs Black-box: Bayes Optimal Strategies for Membership Inference](https://mlsanity.com/paper/1908.11229/) (2019)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [Reconstruction and Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1906.03006/) (2019)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Practical Blind Membership Inference Attack via Differential Comparisons](https://mlsanity.com/paper/2101.01341/) (2021)
- [Differentially Private Synthetic Medical Data Generation using Convolutional GANs](https://mlsanity.com/paper/2012.11774/) (2020)
- [Differentially Private Mixture of Generative Neural Networks](https://mlsanity.com/paper/1709.04514/) (2017)
- [CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records](https://mlsanity.com/paper/2001.09346/) (2020)
- [Generating and designing DNA with deep generative models](https://mlsanity.com/paper/1712.06148/) (2017)
- [EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders](https://mlsanity.com/paper/2012.10020/) (2020)
- [GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1909.03935/) (2019)
- [A systematic comparison of supervised classifiers](https://mlsanity.com/paper/1311.0202/) (2013)
- [Machine learning and genomics: precision medicine vs. patient privacy](https://mlsanity.com/paper/1802.10568/) (2018)

## Built on by (most cited first, 8 of 8)

- [A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data](https://mlsanity.com/paper/2301.10053/) (2023)
- [Systematic Assessment of Tabular Data Synthesis](https://mlsanity.com/paper/2402.06806/) (2024)
- [Can I trust my fake data -- A comprehensive quality assessment framework for synthetic tabular data in healthcare](https://mlsanity.com/paper/2401.13716/) (2024)
- [The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets](https://mlsanity.com/paper/2312.05114/) (2023)
- [A Consensus Privacy Metrics Framework for Synthetic Data](https://mlsanity.com/paper/2503.04980/) (2025)
- [Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directions](https://mlsanity.com/paper/2311.17453/) (2023)
- [Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective](https://mlsanity.com/paper/2601.22434/) (2026)
- [A primer on synthetic health data](https://mlsanity.com/paper/2401.17653/) (2024)

## 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.