CoChat

The Algorithmic Foundations of Differential Privacy

Dwork, Cynthia, Roth, Aaron · 2014 · Foundations and Trends® in Theoretical Computer Science

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Abstract

The problem of privacy-preserving data analysis has a long history spanning multiple disciplines. As electronic data about individuals becomes increasingly detailed, and as technology enables ever more powerful collection and curation of these data, the need increases for a robust, meaningful, and mathematically rigorous definition of privacy, together with a computationally rich class of algorithms that satisfy this definition. Differential Privacy is such a definition. After motivating and discussing the meaning of differential privacy, the preponderance of this monograph is devoted to fundamental techniques for achieving differential privacy, and application of these techniques in creative combinations, using the query-release problem as an ongoing example. A key point is that, by rethinking the computational goal, one can often obtain far better results than would be achieved by methodically replacing each step of a non-private computation with a differentially private implementation. Despite some astonishingly powerful computational results, there are still fundamental limitations — not just on what can be achieved with differential privacy but on what can be achieved with any method that protects against a complete breakdown in privacy. Virtually all the algorithms discussed herein maintain differential privacy against adversaries of arbitrary computational power. Certain algorithms are computationally intensive, others are efficient. Computational complexity for the adversary and the algorithm are both discussed. We then turn from fundamentals to applications other than queryrelease, discussing differentially private methods for mechanism design and machine learning. The vast majority of the literature on differentially private algorithms considers a single, static, database that is subject to many analyses. Differential privacy in other models, including distributed databases and computations on data streams is discussed. Finally, we note that this work is meant as a thorough introduction to the problems and techniques of differential privacy, but is not intended to be an exhaustive survey — there is by now a vast amount of work in differential privacy, and we can cover only a small portion of it.

Overview

Integrity signals

Registry

Crossref · 10.1561/0400000042

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

The text we found for this paper looks like another document, so its claims and self-check weren’t run. The registry and citation checks still apply.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The text we found for this paper looks like another document, so the self-check wasn’t run.

Citations

Cites

Show all 6 references

Research works printed but not linked: 83

  1. Arora, 2012, The multiplicative weights update method: A meta-algorithm and applications, Theory of Computing, 8, 121, 10.4086/toc.2012.v008a006 · doi:10.4086/toc.2012.v008a006
  2. Balcan, 2005, Mechanism design via machine learning, Foundations of Computer Science, 2005. FOCS 2005. 46th Annual IEEE Symposium on, 605
  3. Beimel, 2010, Bounds on the sample complexity for private learning and private data release, Theory of Cryptography, 437
  4. Beimel, 2013, Characterizing the sample complexity of private learners, Proceedings of the Conference on Innovations in Theoretical Computer Science, 97
  5. Bhaskara, 2012, Unconditional differentially private mechanisms for linear queries, Proceedings of the Symposium on Theory of Computing Conference, Symposium on Theory of Computing, New York, NY, USA, May 19-22, 2012, 1269
  6. Blum, 2005, Practical privacy: the SuLQ framework, Principles of Database Systems, 128
  7. Blum, Practical privacy: the sulq framework, Principles of Database Systems
  8. Blum, 2008, A learning theory approach to noninteractive database privacy, Symposium on Theory of Computing, 609, 10.1145/1374376.1374464 · DOI · Paper page
  9. Blum, 2007, Learning, regret minimization, and equilibria
  10. Casti, Five Golden Rules: Great Theories of 20th-Century Mathematics and Why They Matter
  11. Hubert, 2010, Private and continual release of statistics, Automata, Languages and Programming, 405, 10.1007/978-3-642-14162-1_34 · DOI
  12. Chaudhuri, Sample complexity bounds for differentially private learning, Proceedings of the Annual Conference on Learning Theory (COLT 2011)
  13. Chaudhuri, Differentially private empirical risk minimization, Journal of machine learning research: JMLR
  14. Chaudhuri, 2012, Near-optimal differentially private principal components, Advances in Neural Information Processing Systems 25, 998
  15. Chen, 2013, Truthful mechanisms for agents that value privacy, Association for Computing Machinery Conference on Electronic Commerce
  16. Dandekar, 2012, Privacy auctions for recommender systems, Internet and Network Economics, 309, 10.1007/978-3-642-35311-6_23 · DOI
  17. De, 2012, Lower bounds in differential privacy, Theory of Cryptography Conference, 321
  18. Dinur, 2003, Revealing information while preserving privacy, Proceedings of the Association for Computing Machinery SIGACT- SIGMOD-SIGART Symposium on Principles of Database Systems, 202
  19. Duchi, 2013, Local privacy and statistical minimax rates, arXiv preprint arXiv:1302.3203 · arXiv
  20. Dwork, 2006, Differential privacy, Proceedings of the International Colloquium on Automata, Languages and Programming (ICALP)(2), 1
  21. Dwork, 2006, Our data, ourselves: Privacy via distributed noise generation, EUROCRYPT, 486
  22. Dwork, Differential privacy and robust statistics, Proceedings of the 2009 International Association for Computing Machinery Symposium on Theory of Computing (STOC)
  23. Dwork, 2006, Calibrating noise to sensitivity in private data analysis, Theory of Cryptography Conference ’06, 265
  24. Dwork, 2007, The price of privacy and the limits of lp decoding, Proceedings of the Association for Computing Machinery Symposium on Theory of Computing, 85
  25. Dwork, 2010, On the difficulties of disclosure prevention in statistical databases or the case for differential privacy, Journal of Privacy and Confidentiality, 10.29012/jpc.v2i1.585 · DOI
  26. Dwork, 2010, Differential privacy under continual observation, Proceedings of the Association for Computing Machinery Symposium on Theory of Computing, 715
  27. Dwork, Pan-private streaming algorithms, Proceedings of International Conference on Super Computing
  28. Dwork, 2009, On the complexity of differentially private data release: Efficient algorithms and hardness results, Symposium on Theory of Computing ’09, 381, 10.1145/1536414.1536467 · DOI · Paper page
  29. Dwork, The privacy of the analyst and the power of the state, Foundations of Computer Science
  30. Dwork, Efficient algorithms for privately releasing marginals via convex relaxations, Proceedings of the Annual Symposium on Computational Geometry (SoCG)
  31. Dwork, 2004, Privacy-preserving datamining on vertically partitioned databases, Proceedings of Cryptology 2004, 3152, 528, 10.1007/978-3-540-28628-8_32 · DOI · Paper page
  32. Dwork, 2010, Boosting and differential privacy, Foundations of Computer Science, 51
  33. Dwork, Analyze gauss: Optimal bounds for privacy-preserving pca, Symposium on Theory of Computing
  34. Fleischer, 2012, Approximately optimal auctions for selling privacy when costs are correlated with data, Association for Computing Machinery Conference on Electronic Commerce, 568
  35. Ghosh, 2013, Privacy and coordination: Computing on databases with endogenous participation, Proceedings of the fourteenth ACM conference on Electronic commerce (EC), 543, 10.1145/2482540.2482585 · DOI
  36. Ghosh, Selling privacy at auction, Association for Computing Machinery Conference on Electronic Commerce
  37. Groce, Limits of computational differential privacy in the client/server setting, Proceedings of the Theory of Cryptography Conference
  38. Gupta, 2011, Privately releasing conjunctions and the statistical query barrier, Symposium on Theory of Computing ’11, 803
  39. Gupta, 2012, Iterative constructions and private data release, Theory of Cryptography Conference, 339
  40. Hastad, A pseudorandom generator from any one-way function, SIAM Journal of Computing
  41. Hardt, 2012, A simple and practical algorithm for differentially private data release, Advances in Neural Information Processing Systems 25, 2348
  42. Hardt, 2012, Beating randomized response on incoherent matrices, Proceedings of the Symposium on Theory of Computing, 1255, 10.1145/2213977.2214088 · DOI
  43. Hardt, Beyond worst-case analysis in private singular vector computation, Proceedings of the Symposium on Theory of Computing
  44. Hardt, 2010, A multiplicative weights mechanism for privacy-preserving data analysis, Foundations of Computer Science, 61
  45. Hardt, 2010, On the geometry of differential privacy, Proceedings of the Association for Computing Machinery Symposium on Theory of Computing, 705
  46. Homer, Resolving individuals contributing trace amounts of dna to highly complex mixtures using high- density snp genotyping microarrays, PLoS Genet
  47. Hsu, 2013, arXiv, 1311
  48. Hsu, 2013, Differential privacy for the analyst via private equilibrium computation, Proceedings of the Association for Computing Machinery Symposium on Theory of Computing (STOC), 341
  49. Huang, 2012, The exponential mechanism for so cial welfare: Private, truthful, and nearly optimal, IEEE Annual Symposium on the Foundations of Computer Science (FOCS), 140
  50. Jain, Differentially private online learning, Journal of Machine Learning Research — Proceedings Track
  51. Kapralov, On differentially private low rank approximation, 10.1137/1.9781611973105.101 · DOI
  52. Kearns, 1998, Efficient noise-tolerant learning from statistical queries, Journal of the Association for Computing Machinery (JAssociation for Computing Machinery), 45, 983, 10.1145/293347.293351 · DOI · Paper page
  53. Kearns, 2014, Mechanism design in large games: Incentives and privacy, Proceedings of the 5th conference on Innovations in theoretical computer science (ITCS)
  54. Kifer, Private convex empirical risk minimization and high-dimensional regression, Journal of Machine Learning Research
  55. Ligett, 2012, Take it or leave it: Running a survey when privacy comes at a cost, Internet and Network Economics, 378, 10.1007/978-3-642-35311-6_28 · DOI
  56. Littlestone, 1989, The weighted majority algorithm, Annual Symposium on Foundations of Computer Science, 1989, 256
  57. McGregor, 2010, The limits of two-party differential privacy, Foundations of Computer Science, 81
  58. McSherry, 2007, Mechanism design via differential privacy, Foundations of Computer Science, 94
  59. McSherry, 2007, Mechanism design via differential privacy, Foundations of Computer Science, 94
  60. Mir, 2011, Pan-private algorithms via statistics on sketches, Proceedings of the Association for Computing Machinery SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, 37, 10.1145/1989284.1989290 · DOI
  61. Mironov, On significance of the least significant bits for differential privacy, 10.1145/2382196.2382264 · DOI · Paper page
  62. Mironov, 2009, Computational differential privacy, Proceedings of CRYPTOLOGY, 126
  63. Narayanan, Robust de-anonymization of large sparse datasets (how to break anonymity of the netflix prize dataset), Proceedings of IEEE Symposium on Security and Privacy
  64. Nikolov, 2013, The geometry of differential privacy: the sparse and approximate cases, Symposium on Theory of Computing
  65. Nissim, 2012, Privacy-aware mechanism design, Association for Computing Machinery Conference on Electronic Commerce, 774
  66. Nissim, 2007, Smooth sensitivity and sampling in private data analysis, Proceedings of the Association for Computing Machinery Symposium on Theory of Computing, 75
  67. Nissim, 2012, Approximately optimal mechanism design via differential privacy, Innovations in Theoretical Computer Science, 203, 10.1145/2090236.2090254 · DOI
  68. Pai, 2013, Privacy and mechanism design, SIGecom Exchanges, 10.1145/2509013.2509016 · DOI
  69. Rogers, 2013, arXiv, 1311
  70. Roth, 2010, Differential privacy and the fat-shattering dimension of linear queries, Approximation, Randomization, and Combinatorial Optimization, Algorithms and Techniques, 683, 10.1007/978-3-642-15369-3_51 · DOI
  71. Roth, 2012, Buying private data at auction: the sensitive surveyor’s problem, Association for Computing Machinery SIGecom Exchanges, 11, 1, 10.1145/2325713.2325714 · DOI
  72. Roth, 2010, Interactive privacy via the median mechanism, Symposium on Theory of Computing ’10, 765
  73. Roth, Conducting truthful surveys, cheaply, Proceedings of the ACM Conference on Electronic Commerce
  74. Rubinstein, 2009, arXiv, 0911
  75. Schapire, 2003, The boosting approach to machine learning: An overview, 10.1007/978-0-387-21579-2_9 · DOI · Paper page
  76. Schapire, 1999, Improved boosting algorithms using confidence-rated predictions, Machine Learning, 39, 297, 10.1023/A:1007614523901 · DOI · Paper page
  77. Schapire, Boosting: Foundations and Algorithms
  78. Smith, Differentially private feature selection via stability arguments, and the robustness of the lasso, Proceedings of Conference on Learning Theory
  79. Sweeney, 1997, Weaving technology and policy together to maintain confidentiality, Journal of Law, Medicines Ethics, 25, 98, 10.1111/j.1748-720X.1997.tb01885.x · DOI · Paper page
  80. Ullman, 2013, Answering n{2+o(1)} counting queries with differential privacy is hard, Symposium on Theory of Computing, 361
  81. Valiant, 1984, A theory of the learnable, Communications of the Association for Computing Machinery, 27, 1134, 10.1145/1968.1972 · DOI · Paper page
  82. Warner, 1965, Randomized response: A survey technique for eliminating evasive answer bias, Journal of the American Statistical Association, 60, 63, 10.1080/01621459.1965.10480775 · DOI · Paper page
  83. Xiao, 2013, Is privacy compatible with truthfulness, Proceedings of the Conference on Innovations in Theoretical Computer Science, 67

Cited by

Metadata

Authors
Dwork, C., & Roth, A.
Affiliations
  • Microsoft (United States) (US)
  • University of Pennsylvania (US)
Venue
Foundations and Trends® in Theoretical Computer Science
Publisher
Emerald
Published
2014-08-11
Volume
9
Issue
3-4
Pages
211-487
ISSN
  • 1551-305X (ISSN-L)
  • 1551-3068
OpenAlex
W4205228770
Cited by
5,557
References
6
Citations by year
2026: 887 · 2025: 822 · 2024: 755 · 2023: 706 · 2022: 602 · 2021: 562 · 2020: 473 · 2019: 297 · 2018: 194 · 2017: 150 · 2016: 73 · 2015: 28 · 2014: 6
FWCI
85.31
Type
journal article
Language
en
Open access
closed
Locations
  • Foundations and Trends® in Theoretical Computer Science (publishedVersion)
  • ELARTU (Ternopil National Technical University) (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
  • Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
Keywords
differential privacy, privacy-preserving data analysis, privacy definitions, computational complexity, mechanism design, distributed databases, data streams

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.