Exposed! A Survey of Attacks on Private Data
The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Privacy-preserving statistical data analysis addresses the general question of protecting privacy when publicly releasing information about a sensitive dataset. A privacy attack takes seemingly innocuous released information and uses it to discern the private details of individuals, thus demonstrating that such information compromises privacy. For example, re-identification attacks have shown that it is easy to link supposedly de-identified records to the identity of the individual concerned. This survey focuses on attacking aggregate data, such as statistics about how many individuals have a certain disease, genetic trait, or combination thereof. We consider two types of attacks: reconstruction attacks, which approximately determine a sensitive feature of all the individuals covered by the dataset, and tracing attacks, which determine whether or not a target individual's data are included in the dataset. We also discuss techniques from the differential privacy literature for releasing approximate aggregate statistics while provably thwarting any privacy attack.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Self-citationThe 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
Self-citationDwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“F or p er so na l u se o nl y. individual can be learnt from the released information, which can only be achieved by releasing no information (Dwork 2006, Dwork & Naor 2008).”
BackgroundSelf-citationRobust De-anonymization of Large Sparse Datasets
Narayanan, A., & Shmatikov, V. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.33 · Cited by 2,372
IX. On the problem of the most efficient tests of statistical hypotheses
Neyman, J., & Pearson, E. S. (1933) · Philosophical Transactions of the Royal Society of London. Series A, Containing Papers of a Mathematical or Physical Character · doi:10.1098/rsta.1933.0009 · Cited by 2,341
Our Data, Ourselves: Privacy Via Distributed Noise Generation
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835
Self-citationHomer, 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 · cited 2×
“By linking public, not anonymous records, such as voter registration records, with de-identified data, strangers can do this too (Sweeney 1997, Narayanan & Shmatikov 2008).”
BackgroundRevealing information while preserving privacy
Dinur, I., & Nissim, K. (2003) · Proceedings of the twenty-second ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems · doi:10.1145/773153.773173 · Cited by 980 · cited 4×
“Theorem 1 (Dinur & Nissim 2003).”
BackgroundInfluentialConcentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
Bun, M., & Steinke, T. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-662-53641-4_24 · Cited by 584
Self-citationA learning theory approach to non-interactive database privacy
Blum, A., Ligett, K., & Roth, A. (2008) · Proceedings of the fortieth annual ACM symposium on Theory of computing · doi:10.1145/1374376.1374464 · Cited by 505 · cited 1×
“In particular, if the data is inherently low-dimensional (e.g., the data of each individual is described by d bits), there are differentially private mechanisms that can answer many more queries (e.g., k ≈ 2σ 2n/ √ d queries, each with error σ ) (Blum et al. 2008, Hardt & Rothblum 2010).”
Background
Research works printed but not linked: 8
- Bassily R, 2016, ACM SIGACT Symp. Theory Comput., 1046
- Dwork C, 2015, Advances in Neural Information Processing Systems 28, 2350
- Dwork C, 2008, J. Priv. Confid., 2, 8
- Hardt M, Miklau G, Pierce B, Roth A. 2012. Slides and video for tutorial presentations. DIMACS Worksh. Recent Work on Differ. Priv. across Comput. Sci., Oct. 24–26. http://dimacs.rutgers.edu/Workshops/DifferentialPrivacy/Slides/slides.html
- Ligett K. 2013. Slides and archived video tutorials. Simons Inst. Worksh. on Big Data and Differ. Priv., Berkeley, CA, Dec. 11–14.https://simons.berkeley.edu/workshops/schedule/78
- Pres. Counc. Advis. Sci. Technol., 2014, Report to the President: Big Data and Privacy: A Technological Perspective.
- Quadrianto N, 2009, J. Mach. Learn. Res., 10, 2349
- Steinke T, 2015, JMLR Worksh. Conf. Proc., 40, 1
Cited by
Nasr, M., Shokri, R., & Houmansadr, A. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00065 · Cited by 1,760
“membership inference) attacks, and reconstruction attacks [1].”
Secure, privacy-preserving and federated machine learning in medical imaging
Kaissis, G. A., Makowski, M. R., Rückert, D., & Braren, R. F. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0186-1 · Cited by 1,676
Membership Inference Attacks From First Principles
Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., & Tramèr, F. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833649 · Cited by 502
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
“The membership inference attacks have mostly been studied for analyzing dataprivacy withrespecttosimple statisticallinear functions [5, 17, 18, 23, 42, 43].”
BackgroundPrivacy preservation in federated learning: An insightful survey from the GDPR perspective
Truong, N., Sun, K., Wang, S., Guitton, F., & Guo, Y. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102402 · Cited by 399
“intended features can be exploited to infer some information about the training data samples. FL systems, consequently, is vulnerable to inference attacks (i.e., membership and reconstruction attacks [89]). Furthermore, local nodes not only passively contribute local training results but also get updated about interme…”
Background
Metadata
- Authors
- Dwork, C., Smith, A., Steinke, T., & Ullman, J.
- Affiliations
- Microsoft (United States) (US)
- Pennsylvania State University (US)
- Harvard University (US)
- Northeastern University (US)
- Venue
- Annual Review of Statistics and Its Application
- Publisher
- Annual Reviews
- Published
- 2017-03-07
- Volume
- 4
- Issue
- 1
- Pages
- 61-84
- ISSN
- 2326-8298 (ISSN-L)
- 2326-831X
- OpenAlex
- W2520881573
- Cited by
- 259
- References
- 35
- Citations by year
- 2026: 18 · 2025: 35 · 2024: 35 · 2023: 33 · 2022: 28 · 2021: 43 · 2020: 26 · 2019: 23 · 2018: 12 · 2017: 6
- FWCI
- 2.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Annual Review of Statistics and Its Application (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
- Keywords
- privacy attacks, aggregated data, re-identification, reconstruction attacks, differential privacy, privacy-preserving data publishing, de-identified data, sensitive attributes
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: Exposed! A Survey of Attacks on Private Data. https://app.cochat.ai/papers/10.1146/annurev-statistics-060116-054123
- The paper
- Dwork, C., Smith, A., Steinke, T., & Ullman, J. (2017). Exposed! A Survey of Attacks on Private Data. Annual Review of Statistics and Its Application. https://doi.org/10.1146/annurev-statistics-060116-054123
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.