The DOI matches its Crossref record; 245 of the 245 references it cites were found in a registry or an index.
Membership Inference Attacks on Machine Learning: A Survey
Open accessAbstract
Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach. For example, via identifying the fact that a clinical record that has been used to train a model associated with a certain disease, an attacker can infer that the owner of the clinical record has the disease with a high chance. In recent years, MIAs have been shown to be effective on various ML models, e.g., classification models and generative models. Meanwhile, many defense methods have been proposed to mitigate MIAs. Although MIAs on ML models form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this article, we conduct the first comprehensive survey on membership inference attacks and defenses. We provide the taxonomies for both attacks and defenses, based on their characterizations, and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain. To further help the researchers, we have created an online resource repository, which we will keep updated with future relevant work. Interested readers can find the repository at https://github.com/HongshengHu/membership-inference-machine-learning-literature.
Overview
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
Verification
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.
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
Items 201–245 of 245
Modelling and Quantifying Membership Information Leakage in Machine LearningPreprint
Farokhi, F., & Kâafar, M. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.10648 · Cited by 40
Quantifying Membership Privacy via Information Leakage
Saeidian, S., Cervia, G., Oechtering, T. J., & Skoglund, M. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3073804 · Cited by 37
Sampling Attacks: Amplification of Membership Inference Attacks by Repeated QueriesPreprint
Rahimian, S., Orekondy, T., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00395 · Cited by 36
Chen, J., Wang, H., Gao, H., & Shi, X. M. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467445 · Cited by 36
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy ProtectionPreprint
Wu, B., Zhao, S., Chen, C., Xu, H., Wang, L., Zhang, X., Sun, G., & Zhou, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07882 · Cited by 35
Self-citationLabel-Leaks: Membership Inference Attack with Label.Preprint
Li, Z., & Yan, S. (2020) · arXiv (Cornell University) · Cited by 34
Zou, Y., Zhang, Z., Michael Backes, A., & Zhang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.04872 · Cited by 34
The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services
Miao, Y., Xue, M., Chen, C., Pan, L., Zhang, J., Zhao, B. Z. H., Kaafar, D., & Xiang, Y. (2020) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2021-0012 · Cited by 33
Resisting membership inference attacks through knowledge distillation
Zheng, J., Cao, Y., & Wang, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.082 · Cited by 33
Comparing Local and Central Differential Privacy Using Membership Inference Attacks
Bernau, D., Robl, J., Grassal, P. W., Schneider, S., & Kerschbaum, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-81242-3_2 · Cited by 33
When Machine Unlearning Jeopardizes Privacy
Chen, M., Zhang, Z., Wang, T., Michael Backes, A., Humbert, M., & Zhang, Y. (2021) · Figshare · doi:10.60882/cispa.24613773 · Cited by 33
Privacy-Preserving in Defending against Membership Inference Attacks
Ying, Z., Zhang, Y., & Liu, X. (2020) · doi:10.1145/3411501.3419428 · Cited by 27
Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning.Preprint
Yaghini, M., Kulynych, B., & Troncoso, C. (2019) · arXiv (Cornell University) · Cited by 25
Membership Inference Attacks on Deep Regression Models for NeuroimagingPreprint
Gupta, U., Stripelis, D., Lam, P., Thompson, P. M., Ambite, J. L., & Steeg, G. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02866 · Cited by 23
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Wu, B., Chen, C., Zhao, S., Chen, C., Yao, Y., Sun, G., Wang, L., Zhang, X., & Zhou, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6107 · Cited by 22
Self-citationData and Model Dependencies of Membership Inference AttackPreprint
Tonni, S. M., Vatsalan, D., Farokhi, F., Kaafar, D., Lu, Z., & Tangari, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.06856 · Cited by 22
Membership Inference Attacks on Knowledge GraphsPreprint
Wang, Y., Huang, L., Yu, P. S., & Sun, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.08273 · Cited by 22
Self-citationDemystifying the Membership Inference Attack
Irolla, P., & Châtel, G. (2019) · doi:10.1109/cmi48017.2019.8962136 · Cited by 21
Shah, M. A., Szurley, J., Mueller, M., Mouchtaris, A., & Droppo, J. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1188 · Cited by 20
Membership Inference Attacks are Easier on Difficult Problems
Shafran, A., Peleg, S., & Hoshen, Y. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01455 · Cited by 20
EAR: An Enhanced Adversarial Regularization Approach against Membership Inference Attacks
Hu, H., Salcic, Z. A., Dobbie, G., Chen, Y., & Zhang, X. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534381 · Cited by 20
Self-citationMeasuring Membership Privacy on Aggregate Location Time-Series
Pyrgelis, A., Troncoso, C., & Cristofaro, E. D. (2020) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3392154 · Cited by 19
walk2friends: Inferring Social Links from Mobility ProfilesPreprint
Michael Backes, A., Humbert, M., Pang, J., & Zhang, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.08221 · Cited by 16
Defending Privacy Against More Knowledgeable Membership Inference Attackers
Yin, Y., Chen, K., Shou, L., & Chen, G. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467444 · Cited by 16
Zhang, B., Yu, R., Sun, H., Li, Y., Xu, J., & Wang, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.08855 · Cited by 15
A Comprehensive Analysis of Information Leakage in Deep Transfer LearningPreprint
Chen, C., Wu, B., Qiu, M., Wang, L., & Zhou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.01989 · Cited by 15
On the Privacy–Utility Trade-Off in Differentially Private Hierarchical Text Classification
Wunderlich, D., Bernau, D., Aldà, F., Parra‐Arnau, J., & Strufe, T. (2022) · Applied Sciences · doi:10.3390/app122111177 · Cited by 15
Differentially Private Learning Does Not Bound Membership Inference.Preprint
Humphries, T., Rafuse, M., Tulloch, L., Oya, S., Goldberg, I., & Kerschbaum, F. (2020) · arXiv (Cornell University) · Cited by 14
Membership Inference Attack with Multi-Grade Service Models in Edge Intelligence
Wang, K., Hu, Z., Ai, Q., Liu, Q., Chen, M., Liu, K., & Cong, Y. (2021) · IEEE Network · doi:10.1109/mnet.011.2000246 · Cited by 14
Measuring Membership Privacy on Aggregate Location Time-Series
Pyrgelis, A., Troncoso, C., & Cristofaro, E. D. (2020) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/3393691.3394200 · Cited by 12
privGAN: Protecting GANs from membership inference attacks at low costPreprint
Mukherjee, S., Xu, Y., Trivedi, A., & Ferres, J. L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00071 · Cited by 10
Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model MetricsPreprint
Bentley, J., Gibney, D., Hoppenworth, G., & Jha, S. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05669 · Cited by 10
ML defense: against prediction API threats in cloud-based machine learning service
Hou, J., Qian, J., Wang, Y., Li, X., Du, H., & Chen, L. (2019) · International Workshop on Quality of Service · doi:10.1145/3326285.3329042 · Cited by 9
On Inferring Training Data Attributes in Machine Learning ModelsPreprint
Zhao, B. Z. H., Asghar, H. J., Bhaskar, R., & Kâafar, M. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10558 · Cited by 9
Jha, S. K., Jha, S., Ewetz, R., Raj, S., Velasquez, A., Pullum, L., & Swami, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.08097 · Cited by 9
FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box QueriesPreprint
Liew, S. P., & Takahashi, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.14023 · Cited by 9
Generating Private Data Surrogates for Vision Related Tasks
Webster, R., Rabin, J., Simon, L., & Jurie, F. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413067 · Cited by 8
Membership Inference Attacks Against Recommender SystemsPreprint
Zhang, M., Ren, Z., Wang, Z., Ren, P., Chen, Z., Hu, P., & Zhang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08045 · Cited by 8
Killing Four Birds with one Gaussian Process: The Relation between different Test-Time Attacks
Grosse, K., Smith, M. T., & Michael Backes, A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413290 · Cited by 7
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep LearningPreprint
Duddu, V., Boutet, A., & Shejwalkar, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00912 · Cited by 4
Defending Medical Image Diagnostics against Privacy Attacks using Generative MethodsPreprint
Paul, W., Cao, Y., Zhang, M., & Burlina, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03078 · Cited by 4
Source Inference Attacks in Federated LearningPreprint
Hu, H., Salcic, Z. A., Sun, L., Dobbie, G., & Zhang, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05659 · Cited by 4
Self-citationAccuracy-Privacy Trade-off in Deep Ensembles.Preprint
Rezaei, S., Shafiq, Z., & Liu, X. (2021) · arXiv (Cornell University) · Cited by 1
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Sablayrolles, A., Douze, M., Ollivier, Y., Schmid, C., & Jégou, H. (2019) · arXiv · doi:10.48550/arxiv.1908.11229
Cited by
Unleashing the potential of prompt engineering for large language models
Chen, B., Zhang, Z., Langrené, N., & Zhu, S. (2025) · Patterns · doi:10.1016/j.patter.2025.101260 · Cited by 490
Cao, Y., Li, S., Liu, Y., Yan, Z., Dai, Y., Yu, P. S., & Sun, L. (2023) · arXiv · doi:10.48550/arxiv.2303.04226 · Cited by 463
Self-citationWang, Y., Su, Z., Guo, S., Dai, M., Luan, T. H., & Liu, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3263909 · Cited by 357
Trustworthy ai: A computational perspective
Liu, H., Wang, Y., Fan, W., Liu, X., Li, Y., Jain, S., Liu, Y., Jain, A., & Tang, J. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3546872 · Cited by 261
Hashem, R., Ali, N., El Zein, F., Fidalgo, P., & Abu Khurma, O. (2023) · Research and Practice in Technology Enhanced Learning · doi:10.58459/rptel.2024.19023 · Cited by 173
Metadata
- Authors
- Hu, H., Salcic, Z., Sun, L., Dobbie, G., Yu, P. S., & Zhang, X.
- Venue
- ACM Computing Surveys
- Published
- 2022-01-31
- Volume
- 54
- Issue
- 11s
- Pages
- 1-37
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3138815606
- Cited by
- 564
- References
- 245
- FWCI
- 36.92
- Type
- journal article
- Language
- en
- Open access
- bronze
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
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.