CoChat
Sign Up
Cited by 640Privacy-Preserving Technologies in DataCryptography and Data SecurityCloud Data Security Solutions

The DOI matches its Crossref record; 129 of the 133 references it cites were found in a registry or an index, and 2 are not checked yet.

A Comprehensive Survey of Privacy-preserving Federated Learning: A Taxonomy, Review, and Future Directions

Open access
Yin, Xuefei, Zhu, Yanming, Hu, Jiankun·2022·ACM Computing Surveys
DOI 10.1145/3460427
Open this paper in CoChat — free accountOpen PDF

Abstract

The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) has been heralded as a solution to generic privacy-preserving machine learning. However, the challenge of protecting data privacy while maintaining the data utility through machine learning still remains. In this article, we present a comprehensive and systematic survey on the PPFL based on our proposed 5W-scenario-based taxonomy. We analyze the privacy leakage risks in the FL from five aspects, summarize existing methods, and identify future research directions.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3460427

Cites

129 of 131 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Flagged first, then by citations

2 of the 133 references couldn’t be matched to a known paper.

Research works printed but not linked: 101

  1. Agrawal D., Proceedings of the ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems. 247--255
  2. Ahmed A., Proceedings of the International Conference on Intelligent Systems and Control. 1--8.
  3. Amin K., Proceedings of the International Conference on Machine Learning, 97
  4. Bhagoji A. N., Proceedings of the International Conference on Machine Learning, 97
  5. Bickel S., Proceedings of the International Conference on Machine Learning. 81--88
  6. Brutzkus Alon, 2019, Proceedings of the International Conference on Machine Learning, 97
  7. Carlini N., Proceedings of the USENIX Security Symposium. 267--284
  8. Chang H., 2019, Cronus: Robust and heterogeneous collaborative learning with black-box knowledge transfer. arxiv:1912.11279. · arXiv
  9. Chen Hong-You, 2021, Proceedings of the International Conference on Learning Representations.
  10. Cheng K., 2021, et al
  11. Choi Beongjun, 2020, Dong-Jun Han, and Jaekyun Moon.
  12. Choquette-Choo C., 2021, Proceedings of the International Conference on Learning Representations.
  13. Choudhury Olivia, 2019, Proceedings of the NeurIPS Workshop on Machine Learning for Health.
  14. Choudhury O., Proceedings of the European Conference on Artificial Intelligence.
  15. Dai W., Proceedings of the International Conference on Machine Learning. 193--200
  16. Devlin J., 2019, BERT: Pre-training of deep bidirectional transformers for language understanding. arxiv:1810.04805. · arXiv
  17. Dong Y., Proceedings of the International Conference on Information and Communications Security. 684--702
  18. Dwork C., Proceedings of the IEEE Annual Symposium on Foundations of Computer Science. 51--60
  19. A. Elgabli J. Park C. Ben Issaid and M. Bennis. 2021. Harnessing wireless channels for scalable and privacy-preserving federated learning. IEEE Transactions on Communications (2021). A. Elgabli J. Park C. Ben Issaid and M. Bennis. 2021. Harnessing wireless channels for scalable and privacy-preserving federated learning. IEEE Transactions on Communications (2021). · DOI · Paper page
  20. D. Enthoven and Z. Al-Ars. 2020. An overview of federated deep learning privacy attacks and eefensive strategies. arxiv:2004.04676. Retrieved from https://arxiv.org/abs/2004.04676. D. Enthoven and Z. Al-Ars. 2020. An overview of federated deep learning privacy attacks and eefensive strategies. arxiv:2004.04676. Retrieved from https://arxiv.org/abs/2004.04676. · arXiv
  21. S. Feng and H. Yu. 2020. Multi-participant multi-class vertical federated learning. arxiv:2001.11154. Retrieved from https://arxiv.org/abs/2001.11154. S. Feng and H. Yu. 2020. Multi-participant multi-class vertical federated learning. arxiv:2001.11154. Retrieved from https://arxiv.org/abs/2001.11154. · arXiv
  22. Y. Feng X. Yang W. Fang S. Xia and X. Tang. 2020. Practical and bilateral privacy-preserving federated learning. arxiv:2002.09843. Retrieved from https://arxiv.org/abs/2002.09843. Y. Feng X. Yang W. Fang S. Xia and X. Tang. 2020. Practical and bilateral privacy-preserving federated learning. arxiv:2002.09843. Retrieved from https://arxiv.org/abs/2002.09843. · arXiv
  23. Fredrikson M., Proceedings of the USENIX Security Symposium. 17--32
  24. Clement Fung Jamie Koerner Stewart Grant and Ivan Beschastnikh. 2019. Dancing in the dark: Private multi-party machine learning in an untrusted setting. arxiv:1811.09712. Retrieved from https://arxiv.org/abs/1811.09712. Clement Fung Jamie Koerner Stewart Grant and Ivan Beschastnikh. 2019. Dancing in the dark: Private multi-party machine learning in an untrusted setting. arxiv:1811.09712. Retrieved from https://arxiv.org/abs/1811.09712. · arXiv
  25. Gade S., Proceedings of the IEEE Conference on Decision and Control. 184--191
  26. Gao J., Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 283--291
  27. Gentry C., Proceedings of the Annual Cryptology Conference. 75--92
  28. Robin C. Geyer Tassilo Klein and Moin Nabi. 2018. Differentially private federated learning: A client level perspective. arxiv:1712.07557. Retrieved from https://arxiv.org/abs/1712.07557. Robin C. Geyer Tassilo Klein and Moin Nabi. 2018. Differentially private federated learning: A client level perspective. arxiv:1712.07557. Retrieved from https://arxiv.org/abs/1712.07557. · arXiv
  29. Gilad-Bachrach R., 2016, Proceedings of the International Conference on Machine Learning. 201--210
  30. Goldreich O., Proceedings of the ACM Symposium on Theory of Computing. 218--229
  31. Hamer Jenny, 2020, Proceedings of the International Conference on Machine Learning, 119
  32. Hayes J., Proceedings of the Conference on Privacy Enhancing Technologies. 133--152
  33. Hitaj B., Proceedings of the ACM SIGSAC Conference on Computer and Communications Security. 603--618
  34. Janbaz S., Proceedings of the International ISC Conference on Information Security and Cryptology. 7--13
  35. Kairouz P., 2019, et al
  36. Kapralov M., Proceedings of the ACM-SIAM Symposium on Discrete Algorithms. 1395--1414
  37. Karimireddy S. P., Proceedings of the International Conference on Machine Learning, 119
  38. Kawachi A., Proceedings of the International Workshop on Public Key Cryptography. 315--329
  39. Lee S., Proceedings of the International Conference on Machine Learning. 489--496
  40. Li J., Proceedings of the International Conference on Learning Representations.
  41. Li N., Proceedings of the IEEE International Conference on Data Engineering. 106--115
  42. Li Q., Proceedings of the AAAI Conference on Artificial Intelligence. 4642--4649
  43. Li Xiaoxiao, 2021, Proceedings of the International Conference on Learning Representations.
  44. Li Z., 2021, Label-leaks: Membership inference attack with label. arxiv:2007.15528. · arXiv
  45. Liang G., Proceedings of the International Conference on Intelligence and Security Informatics. 66--82
  46. Liu D., 2018, FADL: Federated-autonomous deep learning for distributed electronic health record. arxiv:1811.11400. · arXiv
  47. Liu Na, 2018, C
  48. Liu R., Proceedings of the International Conference on Database Systems for Advanced Applications.
  49. Liu Y., 2019, et al
  50. Lu H., Proceedings of the International Workshop on Federated Learning for User Privacy and Data Confidentiality.
  51. Lu S., Proceedings of the Annual Conference on Information Sciences and Systems. 1--5.
  52. L. Lyu H. Yu and Q. Yang. 2020. Threats to federated learning: A survey. arxiv:2003.02133. Retrieved from https://arxiv.org/abs/2003.02133. L. Lyu H. Yu and Q. Yang. 2020. Threats to federated learning: A survey. arxiv:2003.02133. Retrieved from https://arxiv.org/abs/2003.02133. · arXiv
  53. Malinovskiy G., Proceedings of the International Conference on Machine Learning, 119
  54. McMahan B., 2017, y Arcas
  55. McMahan H. B., Proceedings of the International Conference on Learning Representations.
  56. Mohassel P., Proceedings of the ACM Conference on Computer and Communications Security. 35--52
  57. Mohassel P., Proceedings of the IEEE Symposium on Security and Privacy. 19--38
  58. Mugunthan Vaikkunth, 2019, Proceedings of the NeurIPS 2019 Workshop on Robust AI in Financial Services.
  59. Nasr M., Proceedings of the ACM SIGSAC Conference on Computer and Communications Security. 634--646
  60. Orekondy T., 2019, Proceedings of the NeurIPS Workshop on Federated Learning for Data Privacy and Confidentiality.
  61. 10.5555/3196160.3196245 · DOI
  62. Reich D., 2019, Privacy-preserving classification of personal text messages with secure multi-party computation, Advances in Neural Information Processing Systems, 32, 3757
  63. Riazi M. S., Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems. 1295--1309
  64. Rothchild D., 2020, Proceedings of the International Conference on Machine Learning, 119
  65. Roy A. G., 2019, et al
  66. A. Sannai. 2018. Reconstruction of training samples from loss functions. arxiv:1805.07337. Retrieved from https://arxiv.org/abs/1805.07337. A. Sannai. 2018. Reconstruction of training samples from loss functions. arxiv:1805.07337. Retrieved from https://arxiv.org/abs/1805.07337. · arXiv
  67. Sharma S., Proceedings of the IEEE International Conference on Big Data. 2569--2576
  68. Shokri R., Proceedings of the IEEE Symposium on Security and Privacy. 3--18
  69. Silver David, 2017, et al
  70. A. Singh P. Vepakomma O. Gupta and R. Raskar. 2019. Detailed comparison of communication efficiency of split learning and federated learning. arxiv:1909.09145. Retrieved from https://arxiv.org/abs/1909.09145. A. Singh P. Vepakomma O. Gupta and R. Raskar. 2019. Detailed comparison of communication efficiency of split learning and federated learning. arxiv:1909.09145. Retrieved from https://arxiv.org/abs/1909.09145. · arXiv
  71. Stallings W., Cryptography and Network Security Principles and Practices
  72. Su Lili, 2019, Securing distributed gradient descent in high dimensional statistical learning. ACM Meas. Anal. Comput. Syst. 3, 1
  73. L. Sun J. Qian X. Chen and P. Yu. 2020. LDP-FL: Practical private aggregation in federated learning with local differential privacy. arxiv:2007.15789. Retrieved from https://arxiv.org/abs/2007.15789. L. Sun J. Qian X. Chen and P. Yu. 2020. LDP-FL: Practical private aggregation in federated learning with local differential privacy. arxiv:2007.15789. Retrieved from https://arxiv.org/abs/2007.15789. · arXiv
  74. Szatmari T., Proceedings of the ACM Conference on User Modeling, Adaptation and Personalization. 187--190
  75. Tanuwidjaja H., Proceedings of the International Conference on Machine Learning for Cyber Security. 29--46
  76. Triastcyn A., Proceedings of the IEEE International Conference on Big Data. 2587--2596
  77. Truex S., Proceedings of the ACM International Workshop on Edge Systems, Analytics and Networking. 61--66
  78. Dijk M. Van, Proceedings of the Annual International Conference on the Theory and Applications of Cryptographic Techniques. 24--43
  79. P. Vepakomma O. Gupta T. Swedish and R. Raskar. 2018. Split learning for health: Distributed deep learning without sharing raw patient data. arxiv:1812.00564. Retrieved from https://arxiv.org/abs/1812.00564. P. Vepakomma O. Gupta T. Swedish and R. Raskar. 2018. Split learning for health: Distributed deep learning without sharing raw patient data. arxiv:1812.00564. Retrieved from https://arxiv.org/abs/1812.00564. · arXiv
  80. Wang C., Proceedings of the International Conference on Machine Learning. 1120--1127
  81. Wang G., Proceedings of the IEEE International Conference on Big Data. 2597--2604
  82. Lixu Wang Shichao Xu Xiao Wang and Qi Zhu. 2019. Eavesdrop the composition proportion of training labels in federated learning. arxiv:1910.06044. Retrieved from https://arxiv.org/abs/1910.06044. Lixu Wang Shichao Xu Xiao Wang and Qi Zhu. 2019. Eavesdrop the composition proportion of training labels in federated learning. arxiv:1910.06044. Retrieved from https://arxiv.org/abs/1910.06044. · arXiv
  83. Wang Y., Proceedings of the AAAI Conference on Artificial Intelligence. 6283--6290
  84. Wang Z., Proceedings of the IEEE Conference on Computer Communications. 2512--2520
  85. Wei W., Proceedings of the European Symposium on Research in Computer Security. 545--566
  86. Wu M., 2021, et al
  87. Xie Chulin, 2020, Proceedings of the International Conference on Learning Representations.
  88. Xu R., Proceedings of the ACM Workshop on Artificial Intelligence and Security. 13--23
  89. K. Yang T. Fan T. Chen Y. Shi and Q. Yang. 2019. A quasi-Newton method based vertical federated learning framework for logistic regression. arxiv:1912.00513. Retrieved from https://arxiv.org/abs/1912.00513. K. Yang T. Fan T. Chen Y. Shi and Q. Yang. 2019. A quasi-Newton method based vertical federated learning framework for logistic regression. arxiv:1912.00513. Retrieved from https://arxiv.org/abs/1912.00513. · arXiv
  90. al S. Yang, 2019, Proceedings of the IJCAI’19 Workshop on Federated Machine Learning for User Privacy and Data Confidentiality.
  91. Yoon Tehrim, 2021, Proceedings of the International Conference on Learning Representations.
  92. Yu Chen, 2019, Proceedings of the International Conference on Machine Learning. 7202--7212
  93. Yu Felix, 2020, Proceedings of the International Conference on Machine Learning. 10946--10956
  94. al H. Yu, 2019, Proceedings of the AAAI Conference on Artificial Intelligence, 33
  95. Zantedeschi V., Proceedings of the International Conference on Artificial Intelligence and Statistics. 864--874
  96. Zhang C., Proceedings of the USENIX Annual Technical Conference. 493--506
  97. Zhang D., Proceedings of the IEEE 3rd International Conference on Data Science in Cyberspace. 652--658
  98. Zhang J., Proceedings of the IEEE Global Communications Conference. 1--6.
  99. Zhang X., Proceedings of the IEEE International Conference on Communications. 1--6.
  100. H. Zhu Z. Li M. Cheah and M. Goh. 2020. Privacy-preserving weighted federated learning within oracle-aided MPC framework. arxiv:2003.07630. Retrieved from https://arxiv.org/abs/2003.07630. H. Zhu Z. Li M. Cheah and M. Goh. 2020. Privacy-preserving weighted federated learning within oracle-aided MPC framework. arxiv:2003.07630. Retrieved from https://arxiv.org/abs/2003.07630. · arXiv
  101. Zhu Y., Proceedings of the International Workshop on Machine Learning in Medical Imaging. 542--551

Cited by

Sorted by citations

See all 640

Related

See all

Metadata

Authors
Yin, X., Zhu, Y., & Hu, J.
Affiliations
  • UNSW Canberra (AU)
  • UNSW Sydney (AU)
ORCID
Venue
ACM Computing Surveys
Publisher
Association for Computing Machinery (ACM)
Published
2021-07-13
Volume
54
Issue
6
Pages
1-36
ISSN
  • 0360-0300 (ISSN-L)
  • 1557-7341
DOI
10.1145/3460427
OpenAlex
W3180608480
Cited by
638
References
133
Citations by year
2026: 108 · 2025: 173 · 2024: 163 · 2023: 122 · 2022: 67 · 2021: 5
FWCI
31.54
Type
journal article
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM Computing Surveys (publishedVersion)
  • Griffith Research Online (submittedVersion)
Funders
ARC (DP190103660;LP180100663)
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
privacy-preserving federated learning, federated learning, privacy leakage, data privacy, data utility, model aggregation, privacy-preserving machine learning, taxonomy (general classification scheme)

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