Abstract
A methodology for practical secure privacy-preserving distributed machine (deep) learning is proposed via addressing the core issues of fully homomorphic encryption, differential privacy, and scalable fast machine learning. Considering that private data is distributed and the training data may contain directly or indirectly an information about private data, an architecture and a methodology are suggested for
-
1.
mitigating the impracticality issue of fully homomorphic encryption (arising from large computational overhead) via very fast gate-by-gate bootstrapping and introducing a learning scheme that requires homomorphic computation of only efficient-to-evaluate functions;
-
2.
addressing the privacy-accuracy tradeoff issue of differential privacy via optimizing the noise adding mechanism;
-
3.
defining an information theoretic measure of privacy-leakage for the design and analysis of privacy-preserving schemes; and
-
4.
addressing the optimal model size determination issue and computationally fast training issue of scalable and fast machine (deep) learning with an alternative approach based on variational learning.
A biomedical application example is provided to demonstrate the application potential of the proposed methodology.
Supported by the Austrian Research Promotion Agency (FFG) Project PRIMAL (Privacy Preserving Machine Learning for Industrial Applications); FFG Project SMiLe (Secure Machine Learning Applications with Homomorphically Encrypted Data); FFG COMET-Modul S3AI (Security and Safety for Shared Artificial Intelligence); FFG Sub-Project PETAI (Privacy Secured Explainable and Transferable AI for Healthcare Systems); EU Horizon 2020 Project SERUMS (Securing Medical Data in Smart Patient-Centric Healthcare Systems); the BMK; the BMDW; and the Province of Upper Austria in the frame of the COMET Programme managed by FFG.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318. Association for Computing Machinery, New York (2016)
Balle, B., Wang, Y.: Improving the gaussian mechanism for differential privacy: analytical calibration and optimal denoising. CoRR abs/1805.06530 (2018)
Basciftci, Y.O., Wang, Y., Ishwar, P.: On privacy-utility tradeoffs for constrained data release mechanisms. In: 2016 Information Theory and Applications Workshop (ITA), pp. 1–6 (2016)
Brakerski, Z.: Fully homomorphic encryption without modulus switching from classical GapSVP. In: Safavi-Naini, R., Canetti, R. (eds.) CRYPTO 2012. LNCS, vol. 7417, pp. 868–886. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32009-5_50
Brakerski, Z., Gentry, C., Vaikuntanathan, V.: (leveled) fully homomorphic encryption without bootstrapping. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ITCS 2012, pp. 309–325. Association for Computing Machinery, New York (2012)
Calmon, F.D.P., Fawaz, N.: Privacy against statistical inference. In: Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2012 (2012)
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 2172–2180. Curran Associates, Inc. (2016)
Cheon, J.H., Coron, J.-S., Kim, J., Lee, M.S., Lepoint, T., Tibouchi, M., Yun, A.: Batch fully homomorphic encryption over the integers. In: Johansson, T., Nguyen, P.Q. (eds.) EUROCRYPT 2013. LNCS, vol. 7881, pp. 315–335. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38348-9_20
Chillotti, I., Gama, N., Georgieva, M., Izabachène, M.: Faster fully homomorphic encryption: bootstrapping in less than 0.1 seconds. In: Cheon, J.H., Takagi, T. (eds.) ASIACRYPT 2016. LNCS, vol. 10031, pp. 3–33. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-53887-6_1
Chillotti, I., Gama, N., Georgieva, M., Izabachène, M.: Faster packed homomorphic operations and efficient circuit bootstrapping for TFHE. In: Takagi, T., Peyrin, T. (eds.) ASIACRYPT 2017. LNCS, vol. 10624, pp. 377–408. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70694-8_14
Chillotti, I., Gama, N., Georgieva, M., Izabachène, M.: TFHE: fast fully homomorphic encryption library (2016). https://tfhe.github.io/tfhe/
Coron, J.-S., Mandal, A., Naccache, D., Tibouchi, M.: Fully homomorphic encryption over the integers with shorter public keys. In: Rogaway, P. (ed.) CRYPTO 2011. LNCS, vol. 6841, pp. 487–504. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-22792-9_28
van Dijk, M., Gentry, C., Halevi, S., Vaikuntanathan, V.: Fully homomorphic encryption over the integers. In: Gilbert, H. (ed.) EUROCRYPT 2010. LNCS, vol. 6110, pp. 24–43. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13190-5_2
Ducas, L., Micciancio, D.: FHEW: bootstrapping homomorphic encryption in less than a second. In: Oswald, E., Fischlin, M. (eds.) EUROCRYPT 2015. LNCS, vol. 9056, pp. 617–640. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-46800-5_24
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our data, ourselves: privacy via distributed noise generation. In: Vaudenay, S. (ed.) EUROCRYPT 2006. LNCS, vol. 4004, pp. 486–503. Springer, Heidelberg (2006). https://doi.org/10.1007/11761679_29
Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Fan, J., Vercauteren, F.: Somewhat practical fully homomorphic encryption. IACR Cryptol. ePrint Arch. 2012, 144 (2012). http://eprint.iacr.org/2012/144
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22Nd ACM SIGSAC Conference on Computer and Communications Security, CCS 2015, pp. 1322–1333. ACM, New York (2015)
Geng, Q., Kairouz, P., Oh, S., Viswanath, P.: The staircase mechanism in differential privacy. IEEE J. Sel. Topics Signal Process. 9(7), 1176–1184 (2015)
Geng, Q., Viswanath, P.: The optimal noise-adding mechanism in differential privacy. IEEE Trans. Inf. Theory 62(2), 925–951 (2016)
Geng, Q., Viswanath, P.: Optimal noise adding mechanisms for approximate differential privacy. IEEE Trans. Inf.Theory 62(2), 952–969 (2016)
Geng, Q., Ding, W., Guo, R., Kumar, S.: Optimal noise-adding mechanism in additive differential privacy. CoRR abs/1809.10224 (2018)
Gentry, C.: Fully homomorphic encryption using ideal lattices. In: STOC 2009, pp. 169–178. Association for Computing Machinery, New York (2009)
Gentry, C., Sahai, A., Waters, B.: Homomorphic encryption from learning with errors: conceptually-simpler, asymptotically-faster, attribute-based. In: Canetti, R., Garay, J.A. (eds.) CRYPTO 2013. LNCS, vol. 8042, pp. 75–92. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40041-4_5
Ghosh, A., Roughgarden, T., Sundararajan, M.: Universally utility-maximizing privacy mechanisms. SIAM J. Comput. 41(6), 1673–1693 (2012)
Gupte, M., Sundararajan, M.: Universally optimal privacy mechanisms for minimax agents. In: Proceedings of the Twenty-ninth ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, PODS 2010, pp. 135–146. ACM, New York (2010)
Huang, C., Kairouz, P., Chen, X., Sankar, L., Rajagopal, R.: Context-aware generative adversarial privacy. Entropy 19(12), 656 (2017)
Kifer, D., Machanavajjhala, A.: No free lunch in data privacy. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, SIGMOD 2011, pp. 193–204. Association for Computing Machinery, New York (2011)
Kumar, M., Freudenthaler, B.: Fuzzy membership functional analysis for nonparametric deep models of image features. IEEE Trans. Fuzzy Syst. 28(12), 3345–3359 (2020)
Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: Deriving an optimal noise adding mechanism for privacy-preserving machine learning. In: Anderst-Kotsis, G., et al. (eds.) DEXA 2019. CCIS, vol. 1062, pp. 108–118. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-27684-3_15
Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: An optimal \((\epsilon ,\delta )-\)differentially private learning of distributed deep fuzzy models. Inf. Sci. 546, 87–120 (2021)
Kumar, M.: Differentially private transferrable deep learning with membership-mappings. CoRR abs/2105.04615 (2021). https://arxiv.org/abs/2105.04615v6
Kumar, M., Brunner, D., Moser, B.A., Freudenthaler, B.: Variational optimization of informational privacy. In: Kotsis, G., et al. (eds.) DEXA 2020. CCIS, vol. 1285, pp. 32–47. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59028-4_4
Kumar, M., Moser, B., Fischer, L., Freudenthaler, B.: Membership-mappings for data representation learning: a bregman divergence based conditionally deep autoencoder. In: Kotsis, G., et al. (eds.) DEXA 2021. CCIS, vol. 1479, pp. 138–147. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87101-7_14
Kumar, M., Moser, B., Fischer, L., Freudenthaler, B.: Membership-mappings for data representation learning: measure theoretic conceptualization. In: Kotsis, G., et al. (eds.) DEXA 2021. CCIS, vol. 1479, pp. 127–137. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87101-7_13
Kumar, M., Moser, B.A., Fischer, L., Freudenthaler, B.: Information theoretic evaluation of privacy-leakage, interpretability, and transferability for trustworthy AI. CoRR abs/2106.06046 (2021). https://arxiv.org/abs/2106.06046v5
Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: Differentially private learning of distributed deep models. In: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2020 Adjunct, pp. 193–200. Association for Computing Machinery, New York (2020)
Kumar, M., Singh, S., Freudenthaler, B.: Gaussian fuzzy theoretic analysis for variational learning of nested compositions. Int. J. Approx. Reas. 131, 1–29 (2021)
Kumar, M., Zhang, W., Weippert, M., Freudenthaler, B.: An explainable fuzzy theoretic nonparametric deep model for stress assessment using heartbeat intervals analysis. IEEE Trans. Fuzzy Syst. 29(12), 3873–3886 (2021)
Liu, C., Chakraborty, S., Mittal, P.: Dependence makes you vulnberable: Differential privacy under dependent tuples. In: 23rd Annual Network and Distributed System Security Symposium, NDSS 2016, San Diego, California, USA, 21–24 February 2016. The Internet Society (2016)
Nuida, K., Kurosawa, K.: (Batch) fully homomorphic encryption over integers for non-binary message spaces. In: Oswald, E., Fischlin, M. (eds.) EUROCRYPT 2015. LNCS, vol. 9056, pp. 537–555. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-46800-5_21
Phan, N., Wang, Y., Wu, X., Dou, D.: Differential privacy preservation for deep auto-encoders: An application of human behavior prediction. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI 2016, pp. 1309–1316. AAAI Press (2016)
Rebollo-Monedero, D., Forné, J., Domingo-Ferrer, J.: From t-closeness-like privacy to postrandomization via information theory. IEEE Trans. Knowl. Data Eng. 22(11), 1623–1636 (2010)
Regev, O.: On lattices, learning with errors, random linear codes, and cryptography. In: Proceedings of the Thirty-Seventh Annual ACM Symposium on Theory of Computing, STOC 2005, pp. 84–93. Association for Computing Machinery, New York (2005)
Sankar, L., Rajagopalan, S.R., Poor, H.V.: Utility-privacy tradeoffs in databases: an information-theoretic approach. IEEE Trans. Inf. Forensics Secur. 8(6), 838–852 (2013)
Tripathy, A., Wang, Y., Ishwar, P.: Privacy-preserving adversarial networks. In: 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 495–505 (2019)
Wang, Y., Basciftci, Y.O., Ishwar, P.: Privacy-utility tradeoffs under constrained data release mechanisms. CoRR abs/1710.09295 (2017). http://arxiv.org/abs/1710.09295
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, M., Moser, B., Fischer, L., Freudenthaler, B. (2022). Towards Practical Secure Privacy-Preserving Machine (Deep) Learning with Distributed Data. In: Kotsis, G., et al. Database and Expert Systems Applications - DEXA 2022 Workshops. DEXA 2022. Communications in Computer and Information Science, vol 1633. Springer, Cham. https://doi.org/10.1007/978-3-031-14343-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-14343-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14342-7
Online ISBN: 978-3-031-14343-4
eBook Packages: Computer ScienceComputer Science (R0)