On Utility and Privacy in Synthetic Genomic Data
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Training on simulated data mitigates concerns regarding privacy breaches, in which specific individuals can be identified from the training data.
“Training on simulated data mitigates concerns regarding privacy breaches, in which specific individuals can be identified from the training data82,83.”
From Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases (2025) · cites this paper as [82]
The Introduction describes synthetic data as a way to minimize the risk of inferring sensitive information about individuals. But Main Findings says synthetic datasets only sometimes offer better protection against membership inference and do not provide robust protection; the claim omits that important limitation. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
A global reference for human genetic variation
The 1000 Genomes Project Consortium, authors, C., Auton, A., Abecasis, G. R., Steering committee, Altshuler, D. M., Durbin, R. M., Abecasis, G. R., Bentley, D. R., Chakravarti, A., et al. (2015) · Nature · doi:10.1038/nature15393 · Cited by 18,247 · see citing works
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · see citing works
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · see citing works
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · see citing works
Understanding Neural Networks Through Deep VisualizationPreprint
Yosinski, J., Clune, J., Nguyen, A. M., Fuchs, T. J., & Lipson, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06579 · Cited by 1,687 · see citing works
Information processing in dynamical systems: foundations of harmony theory
Smolensky, P. (1986) · The MIT Press eBooks · Cited by 1,673 · see citing works
Genetics in geographically structured populations: defining, estimating and interpreting FST
Holsinger, K. E., & Weir, B. S. (2009) · Nature Reviews Genetics · doi:10.1038/nrg2611 · Cited by 1,422 · see citing works
Identifying Personal Genomes by Surname Inference
Gymrek, M., McGuire, A. L., Golan, D., Halperin, E., & Erlich, Y. (2013) · Science · doi:10.1126/science.1229566 · Cited by 1,228 · see citing works
Homer, N., Szelinger, S., Redman, M., Duggan, D., Tembe, W., Muehling, J., Pearson, J. V., Stephan, D. A., Nelson, S. F., & Craig, D. W. (2008) · PLoS Genetics · doi:10.1371/journal.pgen.1000167 · Cited by 1,221 · see citing works
Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., & Backes, M. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23119 · Cited by 852 · see citing works
Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing.
Fredrikson, M., Lantz, E., Jha, S., Lin, S. M., Page, D., & Ristenpart, T. (2014) · PubMed · Cited by 658 · see citing works
König, I. R., Fuchs, O., Hansen, G., von Mutius, E., & Kopp, M. (2017) · European Respiratory Journal · doi:10.1183/13993003.00391-2017 · Cited by 579 · see citing works
Inceptionism: Going Deeper into Neural Networks
Mordvintsev, A., Olah, C., & Tyka, M. (2015) · Cited by 574 · see citing works
Machine Learning with Membership Privacy using Adversarial Regularization
Nasr, M., Shokri, R., & Houmansadr, A. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243855 · Cited by 458 · see citing works
LOGAN: Membership Inference Attacks Against Generative Models
Hayes, J., Melis, L., Danezis, G., & De Cristofaro, E. (2019) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0008 · Cited by 433 · see citing works
The significance probability of the smirnov two-sample test
Hodges, J. L. (1958) · Arkiv för matematik · doi:10.1007/bf02589501 · Cited by 431 · see citing works
Generating Multi-label Discrete Patient Records using Generative Adversarial NetworksPreprint
Choi, E., Biswal, S., Malin, B., Duke, J. D., Stewart, W. F., & Sun, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06490 · Cited by 422 · see citing works
Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing
Beaulieu‐Jones, B. K., Wu, Z. S., Williams, C., Lee, R., Bhavnani, S. P., Byrd, J. B., & Greene, C. S. (2019) · Circulation Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.118.005122 · Cited by 407 · see citing works
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
Jordon, J., Yoon, J., & van der Schaar, M. (2018) · International Conference on Learning Representations · Cited by 360 · see citing works
Differentially Private Generative Adversarial NetworkPreprint
Xie, L., Lin, K., Wang, S., Wang, F., & Zhou, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06739 · Cited by 322 · see citing works
Anonymization Through Data Synthesis Using Generative Adversarial Networks (ADS-GAN)
Yoon, J., Drumright, L. N., & van der Schaar, M. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2980262 · Cited by 281 · see citing works
Generating high-fidelity synthetic patient data for assessing machine learning healthcare software
Tucker, A., Wang, Z., Rotalinti, Y., & Myles, P. R. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00353-9 · Cited by 230 · see citing works
A systematic comparison of supervised classifiers
Amancio, D. R., Comin, C. H., Casanova, D., Travieso, G., Bruno, O. M., Rodrigues, F. A., & da Fontoura Costa, L. (2014) · PLoS ONE · doi:10.1371/journal.pone.0094137 · Cited by 225 · see citing works
Benner, C., Havulinna, A. S., Järvelin, M., Salomaa, V. V., Ripatti, S., & Pirinen, M. (2017) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2017.08.012 · Cited by 225 · see citing works
Privacy risks from genomic data-sharing beacons
Shringarpure, S. S., & Bustamante, C. D. (2015) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2015.09.010 · Cited by 211 · see citing works
White-box vs Black-box: Bayes Optimal Strategies for Membership InferencePreprint
Sablayrolles, A., Douze, M., Ollivier, Y., Schmid, C., & Jeǵou, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11229 · Cited by 176 · see citing works
Privacy-preserving data exploration in genome-wide association studies
Johnson, A., & Shmatikov, V. (2013) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2487575.2487687 · Cited by 172 · see citing works
Monte Carlo and Reconstruction Membership Inference Attacks against Generative Models
Hilprecht, B., Härterich, M., & Bernau, D. (2019) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0067 · Cited by 158 · see citing works
Differentially private synthetic medical data generation using convolutional GANs
Torfi, A., Fox, E. A., & Reddy, C. K. A. (2021) · Information Sciences · doi:10.1016/j.ins.2021.12.018 · Cited by 149 · see citing works
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
Leino, K., & Fredrikson, M. (2019) · arXiv · doi:10.48550/arxiv.1906.11798 · Cited by 145 · see citing works
Differentially Private Mixture of Generative Neural Networks
Ács, G., Melis, L., Castelluccia, C., & Cristofaro, E. D. (2017) · Proceedings · doi:10.1109/icdm.2017.81 · Cited by 137 · see citing works
Generating and designing DNA with deep generative modelsPreprint
Killoran, N., Lee, L. J., Delong, A., Duvenaud, D., & Frey, B. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.06148 · Cited by 131 · see citing works
Im, H. K., Gamazon, E. R., Nicolae, D. L., & Cox, N. J. (2012) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2012.02.008 · Cited by 103 · see citing works
Practical Blind Membership Inference Attack via Differential Comparisons
Hui, B., Yang, Y., Yuan, H., Burlina, P., Gong, N. Z., & Cao, Y. (2021) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24293 · Cited by 102 · see citing works
Linkage Disequilibrium Between Loci With Unknown Phase
Rogers, A. R., & Huff, C. D. (2009) · Genetics · doi:10.1534/genetics.108.093153 · Cited by 89 · see citing works
Privacy-preserving generative deep neural networks support clinical data sharingPreprint
Beaulieu‐Jones, B. K., Wu, Z. S., Williams, C., et al. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/159756 · Cited by 89 · see citing works
Machine learning and genomics: precision medicine versus patient privacy
Azencott, C.-A. (2018) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2017.0350 · Cited by 89 · see citing works
Non-equilibrium theory of the allele frequency spectrum
Evans, S. N., Shvets, Y., & Slatkin, M. (2006) · Theoretical Population Biology · doi:10.1016/j.tpb.2006.06.005 · Cited by 88 · see citing works
Addressing Beacon re-identification attacks: quantification and mitigation of privacy risks
Raisaro, J. L., Tramèr, F., Ji, Z., Bu, D., Zhao, Y., Carey, K., Lloyd, D., Sofia, H. J., Baker, D. B., Flicek, P., et al. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocw167 · Cited by 86 · see citing works
Wang, S., Jiang, X., Singh, S., Marmor, R., Bonomi, L., Fox, D., Dow, M., & Ohno‐Machado, L. (2017) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.13259 · Cited by 78 · see citing works
Re-identification of individuals in genomic data-sharing beacons via allele inference
von Thenen, N., Ayday, E., & Çiçek, A. E. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty643 · Cited by 78 · see citing works
To Release or Not to Release: Evaluating Information Leaks in Aggregate Human-Genome Data
Zhou, X., Peng, B., Li, Y. F., Chen, Y., Tang, H., & Wang, X. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23822-2_33 · Cited by 66 · see citing works
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
Chen, D., Orekondy, T., & Fritz, M. (2020) · Figshare · doi:10.60882/cispa.24613350 · Cited by 56 · see citing works
Torfi, A., & Fox, E. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.09346 · Cited by 53 · see citing works
Whole Genome Sequencing: Revolutionary Medicine or Privacy Nightmare?
Ayday, E., Cristofaro, E. D., Hubaux, J., & Tsudik, G. (2015) · Computer · doi:10.1109/mc.2015.59 · Cited by 40 · see citing works
Quantifying Genomic Privacy via Inference Attack with High-Order SNV Correlations
Samani, S. S., Huang, Z., Ayday, E., Elliot, M. J., Fellay, J., Hubaux, J., & Kutalik, Z. (2015) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2015.21 · Cited by 39 · see citing works
GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANsPreprint
Chen, D., Yu, N., Zhang, Y., & Fritz, M. (2019) · arXiv (Cornell University) · Cited by 31 · see citing works
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private GeneratorsPreprint
Chen, D., Orekondy, T., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08265 · Cited by 30 · see citing works
Synthetic Data -- A Privacy MiragePreprint
Stadler, T., Oprisanu, B., & Troncoso, C. (2020) · arXiv (Cornell University) · Cited by 23 · see citing works
Self-citationChen, J., Wang, H., & Shi, X. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.08.03.235416 · Cited by 19 · see citing works
Telenti, A., Ayday, E., & Hubaux, J. P. (2014) · F1000Research · doi:10.12688/f1000research.3817.1 · Cited by 11 · see citing works
Genome-Wide Association Studies
Yang, T.-H., Kon, M., & DeLisi, C. (2012) · Methods in molecular biology · doi:10.1007/978-1-62703-107-3_15 · Cited by 11 · see citing works
Disentangling Linkage Disequilibrium and Linkage From Dense Single-Nucleotide Polymorphism Trio Data
Clarke, G. M., & Cardon, L. R. (2005) · Genetics · doi:10.1534/genetics.105.047431 · Cited by 8 · see citing works
EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational AutoencodersPreprint
Biswal, S., Ghosh, S., Duke, J. D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10020 · Cited by 8 · see citing works
Finding hidden treasures in summary statistics from genome-wide association studies
Privé, F., Zhu, Z., & Vilhjálmsson, B. J. (2021) · Nature Genetics · doi:10.1038/s41588-021-00824-z · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 8
- R. A. Fisher. The distribution of gene ratios for rare mutations. Proceedings of the Royal Society of Edinburgh, 50, 1931.
- I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville. Improved Training of Wasserstein GANs. In NeurIPS, 2017.
- M. Humbert, E. Ayday, J.-P. Hubaux, and A. Telenti. Addressing the concerns of the lacks family: quantification of kin genomic privacy. In ACM CCS, 2013.
- M. Naveed, E. Ayday, E. W. Clayton, J. Fellay, C. A. Gunter, J.- P. Hubaux, B. A. Malin, and X. Wang. Privacy In The Genomic Era. ACM Computing Surveys, 48(1), 2015.
- UK Government. Press Release -New synthetic datasets to assist COVID-19 and cardiovascular research. https://bit.ly/ 3eFCFB4, 2020.
- R. Wang, Y. F. Li, X. Wang, H. Tang, and X. Zhou. Learning your identity and disease from research papers: information leaks in genome wide association study. In ACM CCS, 2009.
- Z. Wang, P. Myles, and A. Tucker. Generating and Evaluating Synthetic UK Primary Care Data: Preserving Data Utility & Patient Privacy. In IEEE International Symposium on Computer- Based Medical Systems, 2019.
- B. Yelmen, A. Decelle, L. Ongaro, D. Marnetto, F. Montinaro, C. Furtlehner, L. Pagani, and F. Jay. Creating Artificial Human Genomes Using Generative Models. https://www.biorxiv.org/ content/10.1101/769091v2, 2019. · DOI
Cited by
Sorted by citations
Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
Alsentzer, E., Li, M. M., Kobren, S. N., Noori, A., Undiagnosed Diseases Network, Kohane, I. S., & Zitnik, M. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01749-1 · Cited by 54 · see citing works
- Authors
- Oprisanu, B., Ganev, G., & De Cristofaro, E.
- Affiliations
- University College London (GB)
- ORCID
- Ganev, Georgi
- Venue
- Proceedings 2022 Network and Distributed System Security Symposium
- Publisher
- Internet Society
- Published
- 2022
- OpenAlex
- W4225966089
- Cited by
- 23
- References
- 56
- Citations by year
- 2026: 5 · 2025: 10 · 2024: 4 · 2023: 2 · 2022: 2
- FWCI
- 2.49
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Network and Distributed System Security Symposium (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- privacy-preserving data generation, membership inference attacks, privacy-utility trade-off, generative models, linkage disequilibrium, training data leakage
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
