Document Open Access Logo

Differentially Private Aggregation via Imperfect Shuffling

Authors Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson, Samson Zhou

PDF

File

Thumbnail PDF
PDF
LIPIcs.ITC.2023.17.pdf
  • Filesize: 0.73 MB
  • 22 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Security and privacy → Human and societal aspects of security and privacy
Keywords
  • Differential privacy
  • private summation
  • shuffle model

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

In this paper, we introduce the imperfect shuffle differential privacy model, where messages sent from users are shuffled in an almost uniform manner before being observed by a curator for private aggregation. We then consider the private summation problem. We show that the standard split-and-mix protocol by Ishai et. al. [FOCS 2006] can be adapted to achieve near-optimal utility bounds in the imperfect shuffle model. Specifically, we show that surprisingly, there is no additional error overhead necessary in the imperfect shuffle model.

Cite As Get BibTex

Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Jelani Nelson, and Samson Zhou. Differentially Private Aggregation via Imperfect Shuffling. In 4th Conference on Information-Theoretic Cryptography (ITC 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 267, pp. 17:1-17:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023) https://doi.org/10.4230/LIPIcs.ITC.2023.17

Author Details

Badih Ghazi
  • Google Research, Mountain View, CA, USA
Ravi Kumar
  • Google Research, Mountain View, CA, USA
Pasin Manurangsi
  • Google Research, Mountain View, CA, USA
Jelani Nelson
  • University of California at Berkeley, CA, USA
  • Google Research, Mountain View, CA, USA
Samson Zhou
  • University of California at Berkeley, CA, USA
  • Rice University, Houston, TX, USA

References

  1. Martín Abadi, Andy Chu, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. Deep learning with differential privacy. In CCS, pages 308-318, 2016. Google Scholar
  2. John M Abowd. The US census bureau adopts differential privacy. In KDD, pages 2867-2867, 2018. Google Scholar
  3. Naman Agarwal, Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, and Brendan McMahan. cpSGD: communication-efficient and differentially-private distributed SGD. In NeurIPS, pages 7575-7586, 2018. Google Scholar
  4. Borja Balle, James Bell, Adrià Gascón, and Kobbi Nissim. Differentially private summation with multi-message shuffling. CoRR, abs/1906.09116, 2019. URL: https://arxiv.org/abs/1906.09116.
  5. Borja Balle, James Bell, Adrià Gascón, and Kobbi Nissim. The privacy blanket of the shuffle model. In CRYPTO, pages 638-667, 2019. Google Scholar
  6. Borja Balle, James Bell, Adrià Gascón, and Kobbi Nissim. Private summation in the multi-message shuffle model. In CCS, pages 657-676, 2020. Google Scholar
  7. Borja Balle, Peter Kairouz, Brendan McMahan, Om Dipakbhai Thakkar, and Abhradeep Thakurta. Privacy amplification via random check-ins. In NeurIPS, 2020. Google Scholar
  8. Raef Bassily, Adam D. Smith, and Abhradeep Thakurta. Private empirical risk minimization: Efficient algorithms and tight error bounds. In FOCS, pages 464-473, 2014. Google Scholar
  9. Amos Beimel, Kobbi Nissim, and Eran Omri. Distributed private data analysis: Simultaneously solving how and what. In CRYPTO, pages 451-468, 2008. Google Scholar
  10. Sourav Biswas, Yihe Dong, Gautam Kamath, and Jonathan R. Ullman. CoinPress: Practical private mean and covariance estimation. In NeurIPS, 2020. Google Scholar
  11. Andrea Bittau, Úlfar Erlingsson, Petros Maniatis, Ilya Mironov, Ananth Raghunathan, David Lie, Mitch Rudominer, Ushasree Kode, Julien Tinnés, and Bernhard Seefeld. Prochlo: Strong privacy for analytics in the crowd. In SOSP, pages 441-459, 2017. Google Scholar
  12. T.-H. Hubert Chan, Elaine Shi, and Dawn Song. Optimal lower bound for differentially private multi-party aggregation. In ESA, pages 277-288, 2012. Google Scholar
  13. Xiangyi Chen, Zhiwei Steven Wu, and Mingyi Hong. Understanding gradient clipping in private SGD: A geometric perspective. In NeurIPS, 2020. Google Scholar
  14. Albert Cheu, Adam D. Smith, Jonathan R. Ullman, David Zeber, and Maxim Zhilyaev. Distributed differential privacy via shuffling. In EUROCRYPT, pages 375-403, 2019. Google Scholar
  15. Albert Cheu and Chao Yan. Necessary conditions in multi-server differential privacy. In ITCS, pages 36:1-36:21, 2023. Google Scholar
  16. Bolin Ding, Janardhan Kulkarni, and Sergey Yekhanin. Collecting telemetry data privately. In NIPS, pages 3571-3580, 2017. Google Scholar
  17. Cynthia Dwork, Krishnaram Kenthapadi, Frank McSherry, Ilya Mironov, and Moni Naor. Our data, ourselves: Privacy via distributed noise generation. In EUROCRYPT, pages 486-503, 2006. Google Scholar
  18. Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam D. Smith. Calibrating noise to sensitivity in private data analysis. In TCC, pages 265-284, 2006. Google Scholar
  19. Cynthia Dwork and Aaron Roth. The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci., 9(3-4):211-407, 2014. Google Scholar
  20. Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, and Abhradeep Thakurta. Amplification by shuffling: From local to central differential privacy via anonymity. In SODA, pages 2468-2479, 2019. Google Scholar
  21. Úlfar Erlingsson, Vasyl Pihur, and Aleksandra Korolova. RAPPOR: randomized aggregatable privacy-preserving ordinal response. In CCS, pages 1054-1067, 2014. Google Scholar
  22. Vitaly Feldman, Audra McMillan, and Kunal Talwar. Hiding among the clones: A simple and nearly optimal analysis of privacy amplification by shuffling. In FOCS, pages 954-964, 2021. Google Scholar
  23. Vitaly Feldman, Audra McMillan, and Kunal Talwar. Stronger privacy amplification by shuffling for renyi and approximate differential privacy. In SODA, pages 4966-4981, 2023. Google Scholar
  24. Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Rasmus Pagh, and Amer Sinha. Differentially private aggregation in the shuffle model: Almost central accuracy in almost a single message. In ICML, pages 3692-3701, 2021. Google Scholar
  25. Badih Ghazi, Pasin Manurangsi, Rasmus Pagh, and Ameya Velingker. Private aggregation from fewer anonymous messages. In EUROCRYPT, pages 798-827, 2020. Google Scholar
  26. Arpita Ghosh, Tim Roughgarden, and Mukund Sundararajan. Universally utility-maximizing privacy mechanisms. SIAM J. Comput., 41(6):1673-1693, 2012. Google Scholar
  27. Antonious M. Girgis, Deepesh Data, Suhas N. Diggavi, Peter Kairouz, and Ananda Theertha Suresh. Shuffled model of federated learning: Privacy, accuracy and communication trade-offs. IEEE J. Sel. Areas Inf. Theory, 2(1):464-478, 2021. Google Scholar
  28. S. Dov Gordon, Jonathan Katz, Mingyu Liang, and Jiayu Xu. Spreading the privacy blanket: Differentially oblivious shuffling for differential privacy. In ACNS, pages 501-520, 2022. Google Scholar
  29. Andy Greenberg. Apple’s "differential privacy" is about collecting your data - but not your data, June 2016. Google Scholar
  30. Yuval Ishai, Eyal Kushilevitz, Rafail Ostrovsky, and Amit Sahai. Cryptography from anonymity. In FOCS, pages 239-248, 2006. Google Scholar
  31. Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, and Sen Zhao. Advances and open problems in federated learning. Found. Trends Mach. Learn., 14(1-2):1-210, 2021. Google Scholar
  32. Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, and Adam D. Smith. What can we learn privately? SIAM J. Comput., 40(3):793-826, 2011. Google Scholar
  33. Jakub Konečný, H. Brendan McMahan, Felix X. Yu, Peter Richtárik, Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency. CoRR, abs/1610.05492, 2016. URL: https://arxiv.org/abs/1610.05492.
  34. Ios Kotsogiannis, Yuchao Tao, Xi He, Maryam Fanaeepour, Ashwin Machanavajjhala, Michael Hay, and Gerome Miklau. Privatesql: A differentially private SQL query engine. Proc. VLDB Endow., 12(11):1371-1384, 2019. Google Scholar
  35. Stephen Shankland. How google tricks itself to protect chrome user privacy. CNET, October, 2014. Google Scholar
  36. Elaine Shi and Ke Wu. Non-interactive anonymous router. In EUROCRYPT, pages 489-520, 2021. Google Scholar
  37. Shuang Song, Kamalika Chaudhuri, and Anand D. Sarwate. Stochastic gradient descent with differentially private updates. In GlobalSIP, pages 245-248, 2013. Google Scholar
  38. Uri Stemmer. Locally private k-means clustering. J. Mach. Learn. Res., 22:176:1-176:30, 2021. Google Scholar
  39. Uri Stemmer and Haim Kaplan. Differentially private k-means with constant multiplicative error. In NeurIPS, pages 5436-5446, 2018. Google Scholar
  40. Ananda Theertha Suresh, Felix X. Yu, Sanjiv Kumar, and H. Brendan McMahan. Distributed mean estimation with limited communication. In ICML, pages 3329-3337, 2017. Google Scholar
  41. Martin Thomson and Christopher A. Wood. Oblivious http, 2023. URL: https://datatracker.ietf.org/doc/draft-ietf-ohai-ohttp/.
  42. Stanley L Warner. Randomized response: A survey technique for eliminating evasive answer bias. JASA, 60(309):63-69, 1965. Google Scholar
  43. Royce J. Wilson, Celia Yuxin Zhang, William Lam, Damien Desfontaines, Daniel Simmons-Marengo, and Bryant Gipson. Differentially private SQL with bounded user contribution. PoPETS, 2020(2):230-250, 2020. Google Scholar
  44. Mingxun Zhou and Elaine Shi. The power of the differentially oblivious shuffle in distributed privacy mechanisms. IACR Cryptol. ePrint Arch., page 177, 2022. Google Scholar
  45. Mingxun Zhou, Elaine Shi, T.-H. Hubert Chan, and Shir Maimon. A theory of composition for differential obliviousness. In EUROCRYPT, 2023. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact