On the Robustness of Information-Theoretic Privacy Measures and Mechanisms
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from n i.i.d. samples, to design a privacy mechanism which is applied to new fresh samples afterward. In this paper, we study the discrepancy between the privacy-utility guarantees for the empirical distribution, used to design the privacy mechanism, and those for the true distribution, experienced by the privacy mechanism in practice. We first show that, for any privacy mechanism, these discrepancies vanish at speed O(1/√n) with high probability. These bounds follow from our main technical results regarding the Lipschitz continuity of the considered information leakage measures. Then we prove that the optimal privacy mechanisms for the empirical distribution approach the corresponding mechanisms for the true distribution as the sample size n increases, thereby establishing the statistical consistency of the optimal privacy mechanisms. Finally, we introduce and study uniform privacy mechanisms which, by construction, provide privacy to all the distributions within a neighborhood of the estimated distribution and, thereby, guarantee privacy for the true distribution with high probability.
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
Communication Theory of Secrecy Systems
Shannon, C. E. (1949) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1949.tb00928.x · Cited by 9,440 · cited 1×
“One commonly-used information leakage metric is Shannon’s mutual information [30] and its generalizations [31].”
Backgroundk-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571 · cited 1×
“, Shannon’s mutual information [9], [10], k-anonymity [11], differential privacy [12], maximal leakage [13], total variation [14], among others.”
BackgroundThe 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
1,500 scientists lift the lid on reproducibility
Baker, M. (2016) · Nature · doi:10.1038/533452a · Cited by 4,209
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Understanding Machine Learning: From Theory to Algorithms
Shalev-Shwartz, S., & Ben-David, S. (2014) · doi:10.1017/cbo9781107298019 · Cited by 3,115
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 1×
“Makhdoumi et al. [32] showed the connection between the privacy funnel and the information bottleneck proposed by Tishby et al. [33].”
BackgroundRobust 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 · cited 1×
“This modern data publishing issue, also present in politics [6], business [7], and welfare [8] to name a few, requires data disclosure methodologies with provable privacy guarantees, whilst still enabling a desired level of utility to be derived from the disclosed data.”
BackgroundAn Introduction to Computational Learning Theory
Kearns, M. J., & Vazirani, U. (1994) · doi:10.7551/mitpress/3897.001.0001 · Cited by 1,697
Donoho, D. (2017) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2017.1384734 · Cited by 695
The reusable holdout: Preserving validity in adaptive data analysis
Dwork, C., Feldman, V., Hardt, M., Pitassi, T., Reingold, O., & Roth, A. (2015) · Science · doi:10.1126/science.aaa9375 · Cited by 307
Context-Aware Generative Adversarial Privacy
Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. (2017) · Entropy · doi:10.3390/e19120656 · Cited by 156
Self-citationGeneralization in Adaptive Data Analysis and Holdout Reuse
Dwork, C., Feldman, V., Hardt, M., Pitassi, T., Reingold, O., & Roth, A. (2015) · arXiv · doi:10.48550/arxiv.1506.02629 · Cited by 152
Cited by
The Roadmap to 6G Security and Privacy
Porambage, P., Gur, G., Osorio, D. P. M., Liyanage, M., Gurtov, A., & Ylianttila, M. (2021) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2021.3078081 · Cited by 416
Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
Cheng, L., Varshney, K. R., & Liu, H. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12814 · Cited by 261
Post-Quantum Era Privacy Protection for Intelligent Infrastructures
Malina, L., Dzurenda, P., Ricci, S., Hajny, J., Srivastava, G., Matulevicius, R., Affia, A.-A. O., Laurent, M., Sultan, N. H., & Tang, Q. (2021) · IEEE Access · doi:10.1109/access.2021.3062201 · Cited by 111
Privacy in Deep Learning: A Survey
Mireshghallah, F., Taram, M., Vepakomma, P., Singh, A., Raskar, R., & Esmaeilzadeh, H. (2020) · arXiv · doi:10.48550/arxiv.2004.12254 · Cited by 106
“There is a body of work studying information-theoretic based methods for both privacy and fairness, where privacy and fairness are provided through information degradation, through obfuscation or adversarial learning and demonstrated by mutual information reduction [67, 68, 48, 69, 70, 71, 72, 73, 74, 75, 76].”
Background
Metadata
- Authors
- Diaz, M., Wang, H., Calmon, F. P., & Sankar, L.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2020-04
- Volume
- 66
- Issue
- 4
- Pages
- 1949-1978
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W2901601003
- Cited by
- 56
- References
- 13
- FWCI
- 3.57
- Type
- journal article
- Language
- en
- Open access
- green
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.