RECENT PROGRESS OF DIFFERENTIALLY PRIVATE FEDERATED LEARNING WITH THE SHUFFLE MODEL
The emerging of shuffle model has attracted considerable attention of scientists owing to his unique properties in solving the privacy problems in federated learning, specifically the trade off problem between privacy and utility in central and local model. Where, the central model relies on a trusted server which collects users’ raw data and then perturbs it. While in the local model all users perturb their data locally then they send their perturbed data to server. Both models have pron and con. The server in central model enjoys with high accuracy but the users suffer from insufficient privacy in contrast, the local model which provides sufficient privacy at users’ side but the server suffers from limited accuracy. Shuffle model has advanced property of hide position of input messages by perturbing it with perturbation π. Therefore, the scientists considered on adding shuffle model between users and servers to make the server untrusted where the users communicate with the server through the shuffle and boosting the privacy by adding perturbation π for users’ messages without increasing the noise level. Consequently, the usage of modified technique differential privacy federated learning with shuffle model will explores the gap between privacy and accuracy in both models. So this new model attracted many researchers in recent work. In this review, we initiate the analytic learning of a shuffled model for distributed differentially private mechanisms. We focused on the role of shuffle model for solving the problem between privacy and accuracy by summarizing the recent researches about shuffle model and its practical results. Furthermore, we present two types of shuffle, single shuffle and m shuffles with the statistical analysis for each one in boosting the privacy amplification of users with the same level of accuracy by reasoning the practical results of recent papers.
Aledhari M., Razzak R., Parizi R., Saeed F. (2020), Federated learning: a survey on enabling technologies, protocols, and applications, IEEE Access, 8, 140699-140725. Retreived from https://doi.org/10.1109/ACCESS.2020.3013541
Amos B., Kobbi N., and Eran O. (2008), Distributed private data analysis: Simultaneously solving how and what, 28th Annual International Cryptology Conference, Springer, 5157, 451-468.
Amos Beimel., Iftach Haitner., Kobbi Nissim. (2020), Uri Stemmer., On the Round Complexity of the Shuffle Model, arXiv: 2009.13510. Retreived from https://doi.org/10.1007/978-3-030-64378-2_24 DOI: https://doi.org/10.1007/978-3-030-64378-2_24
Balcer V., Cheu A. (2019), Separating local & shuffled differential privacy via histograms, arXiv: 1911.06879.
Balle B., Barthe G., Gaboardi M. (2018), Privacy amplification by sub sampling: Tight analyses via couplings and divergences, ArXiv:1807.01647.
Balle B., Bell J., Gascon A., Nissim K. (2019), The privacy blanket of the shuffle model, arXiv: 1903.02837, Retreived from https://doi.org/10.1007/978-3-030-26951-7_22 DOI: https://doi.org/10.1007/978-3-030-26951-7_22
Bittau A., Erlingsson U., Maniatis P., Mironov I., Raghunathan A., Lie D., Rudominer M., Kode U., Tinnes J., Seefeld B. (2017), PROCHLO: Strong privacy for analytics in the crowd. In Proceedings of the Symposium on Operating Systems Principles (SOSP), 441-459. Retreived from https://doi.org/10.1145/3132747.3132769 DOI: https://doi.org/10.1145/3132747.3132769
Borja Balle, James Bell, Adria Gascon, Kobbi Nissim (2019). Differentially Private Summation with Multi-Message Shuffling. arXiv:1906.09116v1 [cs.CR]. Retreived from https://doi.org/10.1145/3372297.3417242
Borja Balle., James Bell., Adrià Gascón., and Kobbi Nissim. (2020), Private Summation in the Multi-Message Shuffle Model. In Proceedings of the 2020ACM SIGSAC Conference on Computer and Communications Security ,Virtual Event, USA. 9-13, 2020. Retreived from https://doi.org/10.1145/3372297.3417242 DOI: https://doi.org/10.1145/3372297.3417242
C. Dwork. (2011), Affirm foundation for private data analysis, Communications of the ACM, 54(1), 86-95. Retreived from https://doi.org/10.1145/1866739.1866758 DOI: https://doi.org/10.1145/1866739.1866758
Casey Meehan., Amrita Roy Chowdhury., Kamalika Chaudhuri., Somesh Jha. (2021), A Shuffling frame work for local differential privacy, arXiv: 2106.06603v1.
Chen M., Yang Z., Saad W., Yin C., Poor H V., Cui S. (2021), A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks. IEEE Transactions on Wireless Communications, 20(1), 269-283. Retreived from https://doi.org/10.1109/TWC.2020.3024629 DOI: https://doi.org/10.1109/TWC.2020.3024629
Cheu A., Smith A., Ullman J., Zeber D., Zhilyaev M. (2019), Distributed differential privacy via shuffling, 11476, 375-403. Retreived from https://doi.org/10.1007/978-3-030-17653-2_13 DOI: https://doi.org/10.1007/978-3-030-17653-2_13
David Byrd. (2020), Antigoni Polychroniadou., Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications, arXiv: 2010.05867. DOI: https://doi.org/10.1145/3383455.3422562
Ding B., Kulkarni J., Yekhanin S. (2017), Collecting telemetry data privately, in Adv. Neural Inf. Process. Syst., Long Beach, CA, 3571-3580.
Dwork C. (2006), Differential Privacy, Proceedings of the 33rd international conference on automata, languages and programming, 2, 1-12. Retreived from https://doi.org/10.1007/11787006_1 DOI: https://doi.org/10.1007/11787006_1
Dwork C. (2008), Differential privacy: a survey of results, International conference on theory and applications of models of computation, 4978, 1-19. Retreived from https://doi.org/10.1007/978-3-540-79228-4_1 DOI: https://doi.org/10.1007/978-3-540-79228-4_1
Erlingsson Ú., Pihur, V., Korolova, A. (2014), Rappor: Randomized aggregable privacy-preserving ordinal response, Proceedings of the 2014 ACM SIGSAC Conference on computer and communications security, Scottsdale, AZ, USA, 1054-1067. Retreived from https://doi.org/10.1145/2660267.2660348 DOI: https://doi.org/10.1145/2660267.2660348
Farokhi., Farhad. (2021), Distributionally-robust machine learning using locally differentially-private data, springer Science and Business Media LLC. 1-13. Retreived from https://doi.org/10.1007/s11590-021-01765-6 DOI: https://doi.org/10.1007/s11590-021-01765-6
Geyer R C., Klein T., Nabi M. (2020), Differentially Private Federated Learning: A Client Level Perspective, IEEE Access, 8, 140699-140725. Retreived from https://doi.org/10.1109/ACCESS.2020.3013541 DOI: https://doi.org/10.1109/ACCESS.2020.3013541
Ghazi B., Golowich N., Kumar R., Manurangsi P., Pagh R., Velingker A., Pure differentially private summation from anonymous messages, arXiv:2002.01919, 2020. Retreived from https://doi.org/10.1007/978-3-030-45724-2_27
Ghazi B., Golowich N., Kumar R., Pagh R., Velingker A. (2020), On the power of multiple anonymous messages, arXiv:1908.11358.
Ghazi B., Golowich N., Kumar R., Manurangsi P., Pagh R., Velingker A. (2020), Pure differentially private summation from anonymous messages, arXiv:2002.01919.
Ghazi B., Manurangsi P., Pagh R., Velingker A. (2020) Private aggregation from fewer anonymous messages. 39th Annual International Conference on the Theory and Applications of Cryptographic Techniques, Zagreb, Croatia, Proceedings, 47,798-827. Retreived from https://doi.org/10.1007/978-3-030-45724-2_27 DOI: https://doi.org/10.1007/978-3-030-45724-2_27
H. B. McMahan, D. Ramage, K. Talwar, and L. Zhang (2018), "Learning Differentially Private Recurrent Language Models," in arXiv:1710.06963 [cs].
H. B. McMahan., D. Ramage., Talwar K., Zhang L. (2018), Learning Differentially Private Recurrent Language Models, arXiv:1710.06963.
Hard A., Rao K., Mathews R., et al. (2018), Federated learning formable keyboard prediction. arXiv preprint arXiv:1811.03604.
Huang L., A. L. Shea., Qian H., Masurkar A., Deng H., Liu D. (2019), Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records, J. Biomed. Informat, 99, 1-21. Retreived from https://doi.org/10.1016/j.jbi.2019.103291 DOI: https://doi.org/10.1016/j.jbi.2019.103291
Huang Xixi., Ding Ye., Jiang Zoe L., Qi Shuhan., Wang Xuan., Liao Qing. (2020), DP-FL: a Novel differentially private federated learning framework for the unbalanced data World Wide Web-internet and Web Information Systems, 23(4), 2529-2545. Retreived from https://doi.org/10.1007/s11280-020-00780-4 DOI: https://doi.org/10.1007/s11280-020-00780-4
Jiang L., Tan R., Lou X., Lin G. (2019), On lightweight privacy preserving collaborative learning for Internet-of-Things objects, in Proc. Int. Conf. Internet Things Design Implement., 70-81. Retreived from https://doi.org/10.1145/3302505.3310070 DOI: https://doi.org/10.1145/3302505.3310070
Jordan Awan., Aleksandra Slavkovi'c. (2018), Structure and Sensitivity in Differential Privacy: Comparing K-Norm Mechanisms, arXiv:1801.09236.
Kairouz P., McMahan H B., et al. (2021) Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning, 14(1), 1-119. Retreived from https://doi.org/10.1561/2200000083 DOI: https://doi.org/10.1561/2200000083
Li T., Sahu K., Talwalkar A., Smith V. (2020), Federated learning challenges, methods, and future directions, IEEE Signal Processing Magazine, 37(3), 50-60. Retreived from https://doi.org/10.1109/MSP.2020.2975749 DOI: https://doi.org/10.1109/MSP.2020.2975749
Li W., Milletarì F.,Xu D.,Rieke N .,Hancox J., Zhu W., Baust M., Cheng Y .,Ourselin S.,J C M ., Feng A. (2019), Privacy-preserving federated brain tumor segmentation, in Proc. Int. Workshop Mach. Learn. Med. Image, 11861,133-141. Retreived from https://doi.org/10.1007/978-3-030-32692-0_16 DOI: https://doi.org/10.1007/978-3-030-32692-0_16
Liu D., Miller T., Sayeed R., Mandl K. (2018), FADL: Federated autonomous deep learning for distributed electronic health record, arXiv:1811.11400.
Liu F. (2019) Generalized Gaussian Mechanism for Differential Privacy, in IEEE Transactions on Knowledge and Data Engineering, 31, 747-756. Retreived from https://doi.org/10.1109/TKDE.2018.2845388 DOI: https://doi.org/10.1109/TKDE.2018.2845388
Liu R., Cao Y. , Chen H., Guo R., Yoshikawa M. (2020), FLAME: Differentially Private Federated Learning in the Shuffle Model, arXiv:2009.08063.
McMahan H., Moore E., Ramage D., Hampson S., and Arcas B. (2016), Communication efficient learning of deep networks from decentralized data, arXiv:1602.05629.
Nakamoto S. (2019), Bitcoin: A Peer-to-Peer Electronic Cash System.Manubot;Online. Retreived from https://metzdowd.com.
NhatHai Phan., Xintao Wu., Han Hu., Dejing Dou. (2017), Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning" IEEE International Conference on Data Mining 17, 2374-8486. DOI: https://doi.org/10.1109/ICDM.2017.48
Qi Liu., Juan Yu., Jianmin Han., Xin Yao. (2021), Differentially private and utility-aware publication of trajectory data, Expert Systems with Applications, 180, 1-14. Retreived from https://doi.org/10.1016/j.eswa.2021.115120. DOI: https://doi.org/10.1016/j.eswa.2021.115120
Ramaswamy S.,Mathews R., Rao K., Beaufays F. (2019), Federated learning for emoji prediction in amobile keyboard, arXiv:1906.04329.
Ren J., Wang H., Hou T., Zheng S., Tang C. (2019), Federated learning-based computation offloading optimization in edge computing supported Internet of Things, IEEE Access, 7, 69194-69201. Retreived from https://doi.org/10.1109/ACCESS.2019.2919736. DOI: https://doi.org/10.1109/ACCESS.2019.2919736
Sarfaraz., Aaliya., Chakrabortty., Ripon K., Essam., Daryl L. (2021), A tree structure-based improved block chain framework for a secure online bidding system, 102, 1-20. Retreived from https://doi.org/10.1016/j.cose.2020.102147 DOI: https://doi.org/10.1016/j.cose.2020.102147
Ulfar Erlingsson., Vitaly Feldman., Ilya Mironov., Ananth Raghunathan., Kunal Talwar. (2019), and Abhradeep Thakurta., Ampliffication by shuffling: From local to central differential privacy via anonymity. the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2468-2479. Retreived from https://doi.org/10.1137/1.9781611975482.151 DOI: https://doi.org/10.1137/1.9781611975482.151
Victor Balcer., Albert Cheu., Matthew Joseph., and Jieming Mao. (2020), Connecting robust shuffle privacy and pan-privacy. arXiv:2004.09481. Retreived from https://doi.org/10.1137/1.9781611976465.142 DOI: https://doi.org/10.1137/1.9781611976465.142
Vitaly Feldman., Ilya Mironov., Kunal Talwar., Abhradeep Thakurta. (2018), Privacy amplification by iteration, In 59th IEEE Annual Symposium on Foundations of Computer Science, Paris, France, 521-532. Retreived from https://doi.org/10.1109/FOCS.2018.00056 DOI: https://doi.org/10.1109/FOCS.2018.00056
Wei K., et al. (2020), "Federated Learning With Differential Privacy: Algorithms and Performance Analysis," in IEEE Transactions on Information Forensics and Security, 15, 3454-3469. Retreived from https://doi.org/10.1109/TIFS.2020.2988575 DOI: https://doi.org/10.1109/TIFS.2020.2988575
Yang Q., Liu Y., Chen T., et al. (2019), Federated machine learning: concept and applications, ACM Transactions on Intelligent Systems and Technology, 10(2), 1-19. Retreived from https://doi.org/10.1145/3298981 DOI: https://doi.org/10.1145/3298981
Yang T., Andrew G., Eichner H., et al. (2018), Applied federated learning: improving google keyboard query suggestions, arXiv:1812.02903.
Zhao L., Wang Q., Zou Q., Zhang Y., Chen Y. (2020), Privacy-Preserving Collaborative Deep Learning With Unreliable Participants, in IEEE Transactions on Information Forensics and Security, 15, 1486-1500. Retreived from https://doi.org/10.1109/TIFS.2019.2939713 DOI: https://doi.org/10.1109/TIFS.2019.2939713
Zhao. P., Zhang, G., Wan, S., Liu, G., Umer, T. (2019), A survey of local differential privacy for securing internet of vehicles. J. Supercomputer, 76, 1-22. Retreived from https://doi.org/10.1007/s11227-019-03104-0 DOI: https://doi.org/10.1007/s11227-019-03104-0
Zhu T., Ye D., Wang W., Zhou W., Yu P. (2020), More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence, IEEE Transactions on Knowledge and Data Engineering. doi: 10.1109/TKDE.2020.3014246. Retreived from https://doi.org/10.1109/TKDE.2020.3014246 DOI: https://doi.org/10.1109/TKDE.2020.3014246
Copyright (c) 2021 Moushira Abdallah Mohamed Ahmed, Shuhui Wu, Laure Deveriane Dushime , Yuanhong Tao
This work is licensed under a Creative Commons Attribution 4.0 International License.
License and Copyright Agreement
In submitting the manuscript to the journal, the authors certify that:
- They are authorized by their co-authors to enter into these arrangements.
- The work described has not been formally published before, except in the form of an abstract or as part of a published lecture, review, thesis, or overlay journal.
- That it is not under consideration for publication elsewhere.
- That its release has been approved by all the author(s) and by the responsible authorities – tacitly or explicitly – of the institutes where the work has been carried out.
- They secure the right to reproduce any material that has already been published or copyrighted elsewhere.
- They agree to the following license and copyright agreement.
Authors who publish with International Journal of Engineering Technologies and Management Research agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or edit it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
For More info, please visit CopyRight Section