privGAN: Protecting GANs from membership inference attacks at low cost to utility
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks such as training classifiers that would otherwise require the original dataset to be shared. However, recent work has shown that the GAN models and their synthetically generated data can be used to infer the training set membership by an adversary who has access to the entire dataset and some auxiliary information. Current approaches to mitigate this problem (such as DPGAN [1]) lead to dramatically poorer generated sample quality than the original non–private GANs. Here we develop a new GAN architecture (privGAN), where the generator is trained not only to cheat the discriminator but also to defend membership inference attacks. The new mechanism is shown to empirically provide protection against this mode of attack while leading to negligible loss in downstream performances. In addition, our algorithm has been shown to explicitly prevent memorization of the training set, which explains why our protection is so effective. The main contributions of this paper are: i) we propose a novel GAN architecture that can generate synthetic data in a privacy preserving manner with minimal hyperparameter tuning and architecture selection, ii) we provide a theoretical understanding of the optimal solution of the privGAN loss function, iii) we empirically demonstrate the effectiveness of our model against several white and black–box attacks on several benchmark datasets, iv) we empirically demonstrate on three common benchmark datasets that synthetic images generated by privGAN lead to negligible loss in downstream performance when compared against non– private GANs. While we have focused on benchmarking privGAN exclusively on image datasets, the architecture of privGAN is not exclusive to image datasets and can be easily extended to other types of datasets. Repository link: https://github.com/microsoft/privGAN.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
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 · cited 2×
“There has been a lot of work on developing membership inference attacks against predictive machine learning models using their outputs [3–6].”
BackgroundThe Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Arjovsky, M., Chintala, S., & Bottou, L. (2017) · arXiv · doi:10.48550/arxiv.1701.07875 · Cited by 2,225
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
Yeom, S., Giacomelli, I., Fredrikson, M., & Jha, S. (2018) · 2018 IEEE 31st Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2018.00027 · Cited by 1,001
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 · cited 2×
“In the classification setting [8] demonstrated adversarial regularization as an effective strategy to prevent membership inference attacks.”
BackgroundPrivacy-Preserving Machine Learning: Threats and Solutions
Al-Rubaie, M., & Chang, J. M. (2019) · IEEE Security & Privacy · doi:10.1109/msec.2018.2888775 · Cited by 444
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
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
Chen, D., Yu, N., Zhang, Y., & Fritz, M. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3417238 · Cited by 311
Cited by
Membership Inference Attacks on Machine Learning: A Survey
Hu, H., Salcic, Z., Sun, L., Dobbie, G., Yu, P. S., & Zhang, X. (2022) · ACM Computing Surveys · doi:10.1145/3523273 · Cited by 564
Protecting Data Privacy in the Age of AI-Enabled Ophthalmology
Tom, E., Keane, P. A., Blazes, M., Pasquale, L. R., Chiang, M. F., Lee, A. Y., Lee, C. S., & and AAO Artificial Intelligence Task Force (2020) · Translational Vision Science & Technology · doi:10.1167/tvst.9.2.36 · Cited by 92
Adversarial Attacks Against Deep Generative Models on Data: A Survey
Sun, H., Zhu, T., Zhang, Z., Jin, D., Xiong, P., & Zhou, W. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130903 · Cited by 90
Survey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
Rajotte, J.-F., Mukherjee, S., Robinson, C., Ortiz, A., West, C., Ferres, J. M. L., & Ng, R. T. (2021) · Proceedings of the Conference on Information Technology for Social Good · doi:10.1145/3462203.3475875 · Cited by 34
Self-citation
Metadata
- Authors
- Mukherjee, S., Xu, Y., Trivedi, A., Patowary, N., & Ferres, J. L.
- Venue
- Proceedings on Privacy Enhancing Technologies
- Published
- 2021-04-27
- Volume
- 2021
- Issue
- 3
- Pages
- 142-163
- ISSN
- 2299-0984 (ISSN-L)
- OpenAlex
- W3159069780
- Cited by
- 38
- References
- 10
- FWCI
- 2.38
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: privGAN: Protecting GANs from membership inference attacks at low cost to utility. https://app.cochat.ai/papers/10.2478/popets-2021-0041
- The paper
- Mukherjee, S., Xu, Y., Trivedi, A., Patowary, N., & Ferres, J. L. (2021). privGAN: Protecting GANs from membership inference attacks at low cost to utility. Proceedings on Privacy Enhancing Technologies. https://doi.org/10.2478/popets-2021-0041
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.