Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
skip to main content
ACM Digital Library home
ACM Association for Computing Machinery corporate logo
Advanced Search

The limits of differential privacy (and its misuse in data release and machine learning)

Authors: Josep Domingo-Ferrer, David Sánchez, and Alberto Blanco-JusticiaAuthors Info & Claims
Communications of the ACM, Volume 64, Issue 7
Pages 33 - 35
https://doi.org/10.1145/3433638
Published: 21 June 2021 Publication History
  • 52citation
  • 6,230
  • Downloads
Metrics
Total Citations52
Total Downloads6,230
Last 12 Months494
Last 6 weeks86
  • Get Citation Alerts
    • All formatsPDF

    Abstract

    Differential privacy is not a silver bullet for all privacy problems.

    References

    [1]
    Abadi, M. et al. Deep learning with differential privacy. In Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security-CCS'16 (2016), 308--318.
    Google Scholar
    [2]
    Bambauer, J., Muralidhar, K., Sarathy, R. Fool's gold: An illustrated critique of differential privacy. Vanderbilt Journal of Entertainment & Technology Law 16 (, 4 (2014), 701--755.
    Google Scholar
    [3]
    Clifton, C., Tassa, T. On syntactic anonymity and differential privacy. Transactions on Data Privacy 6, 2 (2013), 161--183.
    Google Scholar
    [4]
    Cyphers, B. Differential privacy, part 3: Extraordinary claims require extraordinary scrutiny. Accessnow (Nov. 30, 2017); https://bit.ly/3oqOTku
    Google Scholar
    [5]
    Dwork, C., Roth, A. The Algorithmic Foundations of Differential Privacy. Foundations and Trends in Theoretical Computer Science 9, 3--4, (2014).
    Digital Library
    Google Scholar
    [6]
    Francis, P. Dear differential privacy, put up or shut up. Technical Report MPI-SWS-2020-005 (Jan. 2020); https://bit.ly/3whnpkc
    Google Scholar
    [7]
    Fredrikson, M. et al. Privacy in pharmacogenetics: an end-to-end case study of personalized warfarin dosing. In Proceedings of the 23rd USENIX Security Symposium (2014), 17--32.
    Google Scholar
    [8]
    Garfinkel, S., Abowd, J.M., Martindale, C. Understanding database reconstruction attacks on public data. Commun. ACM 62, 3 (Mar. 2019), 46--53.
    Digital Library
    Google Scholar
    [9]
    Greenberg, A. How one of Apple's key privacy safeguards falls short. Wired (Sept. 15, 2017); https://bit.ly/2RsaLjr
    Google Scholar
    [10]
    Kifer, D. and Machanavajjhala, A. No free lunch in data privacy. In Proceedings of the SIGMOD Conference 2011 (2011), 193--204.
    Digital Library
    Google Scholar
    [11]
    Kifer, D. et al. Guidelines for implementing and auditing differentially private systems. (Feb. 10, 2020); https://bit.ly/2RwMHvH
    Google Scholar
    [12]
    Mervis, J. Researchers finally get access to data on Facebook's role in political discourse. Science (Feb. 13, 2020); https://bit.ly/3ynS7Kj
    Google Scholar
    [13]
    Ruggles, S. et al. Differential privacy and Census data: implications for social and economic research. AEA Papers and Proceedings, 109 (2019), 403--408.
    Crossref
    Google Scholar
    [14]
    Santos-Lozada, A.R., Howard, J.T. and Verdery, A.M. How differential privacy will affect our understanding of health disparities in the United States. In Proceedings of the National Academy of Sciences 117, 24) (2020), 13405--13412.
    Crossref
    Google Scholar
    [15]
    Triastcyn, A. and Faltings, B. Federated learning with Bayesian differential privacy. In Proceedings of 2019 IEEE Intl. Conf. on Big Data (2019), 2587--2596.
    Crossref
    Google Scholar
    [16]
    Wei, K. et al. Federated learning with differential privacy: algorithms and performance analysis. IEEE Transactions on Information Forensics and Security, 15 (2020), 3454--3469.
    Digital Library
    Google Scholar

    Cited By

    View all
    • Franzen DMüller-Birn CWegwarth O(2024)Communicating the Privacy-Utility Trade-off: Supporting Informed Data Donation with Privacy Decision Interfaces for Differential PrivacyProceedings of the ACM on Human-Computer Interaction10.1145/36373098:CSCW1(1-56)Online publication date: 26-Apr-2024
      https://dl.acm.org/doi/10.1145/3637309
    • Cheng PEykholt KGu ZJamjoom HJayaram KValdez EVerma A(2024)DeTA: Minimizing Data Leaks in Federated Learning via Decentralized and Trustworthy AggregationProceedings of the Nineteenth European Conference on Computer Systems10.1145/3627703.3650082(219-235)Online publication date: 22-Apr-2024
      https://dl.acm.org/doi/10.1145/3627703.3650082
    • Zhao BChen WLi XLiu XPei QZhang J(2024)When Evolutionary Computation Meets PrivacyIEEE Computational Intelligence Magazine10.1109/MCI.2023.332789219:1(66-74)Online publication date: 1-Feb-2024
      https://dl.acm.org/doi/10.1109/MCI.2023.3327892
    • Show More Cited By

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    Communications of the ACM  Volume 64, Issue 7
    July 2021
    99 pages
    ISSN:0001-0782
    EISSN:1557-7317
    DOI:10.1145/3472147
    Issue’s Table of Contents
    Copyright © 2021 Owner/Author.
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 21 June 2021
    Published in CACM Volume 64, Issue 7

    Check for updates

    Qualifiers

    • Opinion
    • Popular
    • Un-reviewed

    Contributors

    Other Metrics

    View Article Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)494
    • Downloads (Last 6 weeks)86

    Other Metrics

    View Author Metrics

    Citations

    Cited By

    View all
    • Franzen DMüller-Birn CWegwarth O(2024)Communicating the Privacy-Utility Trade-off: Supporting Informed Data Donation with Privacy Decision Interfaces for Differential PrivacyProceedings of the ACM on Human-Computer Interaction10.1145/36373098:CSCW1(1-56)Online publication date: 26-Apr-2024
      https://dl.acm.org/doi/10.1145/3637309
    • Cheng PEykholt KGu ZJamjoom HJayaram KValdez EVerma A(2024)DeTA: Minimizing Data Leaks in Federated Learning via Decentralized and Trustworthy AggregationProceedings of the Nineteenth European Conference on Computer Systems10.1145/3627703.3650082(219-235)Online publication date: 22-Apr-2024
      https://dl.acm.org/doi/10.1145/3627703.3650082
    • Zhao BChen WLi XLiu XPei QZhang J(2024)When Evolutionary Computation Meets PrivacyIEEE Computational Intelligence Magazine10.1109/MCI.2023.332789219:1(66-74)Online publication date: 1-Feb-2024
      https://dl.acm.org/doi/10.1109/MCI.2023.3327892
    • Majeed AHwang S(2023)A Generic Approach towards Enhancing Utility and Privacy in Person-Specific Data Publishing Based on Attribute Usefulness and UncertaintyElectronics10.3390/electronics1209197812:9(1978)Online publication date: 24-Apr-2023
      https://doi.org/10.3390/electronics12091978
    • Muralidhar KDomingo-Ferrer J(2023)Database Reconstruction Is Not So Easy and Is Different from ReidentificationJournal of Official Statistics10.2478/jos-2023-001739:3(381-398)Online publication date: 7-Sep-2023
      https://doi.org/10.2478/jos-2023-0017
    • Szyller SAsokan NWilliams BChen YNeville J(2023)Conflicting interactions among protection mechanisms for machine learning modelsProceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v37i12.26771(15179-15187)Online publication date: 7-Feb-2023
      https://dl.acm.org/doi/10.1609/aaai.v37i12.26771
    • He MHu S(2023)A Normative Approach to Privacy-Preserving Recommender SystemsInternational Journal of Intelligent Systems10.1155/2023/29595032023Online publication date: 1-Jan-2023
      https://dl.acm.org/doi/10.1155/2023/2959503
    • Slavković ASeeman J(2023)Statistical Data Privacy: A Song of Privacy and UtilityAnnual Review of Statistics and Its Application10.1146/annurev-statistics-033121-11292110:1(189-218)Online publication date: 10-Mar-2023
      https://doi.org/10.1146/annurev-statistics-033121-112921
    • Ghosheh GLi JZhu T(2023)A Survey of Generative Adversarial Networks for Synthesizing Structured Electronic Health RecordsACM Computing Surveys10.1145/363642456:6(1-34)Online publication date: 6-Dec-2023
      https://dl.acm.org/doi/10.1145/3636424
    • Molamohammadi MTaïk ALe Roux NFarnadi G(2023)Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive AdvancementsProceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization10.1145/3617694.3623256(1-12)Online publication date: 30-Oct-2023
      https://dl.acm.org/doi/10.1145/3617694.3623256
    • Show More Cited By

    View Options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Digital Edition

    View this article in digital edition.

    Digital Edition

    Magazine Site

    View this article on the magazine site (external)

    Magazine Site

    Get Access

    Login options

    Full Access

    Get this Article

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media

    Download PDF
    View Issue’s Table of Contents