Abstract
The soaring amount of data coming from a variety of sources including social networks and mobile devices opens up new perspectives while at the same time posing new challenges. On one hand, AI-systems like Neural Networks paved the way toward new applications ranging from self-driving cars to text understanding. On the other hand, the management and analysis of data that fed these applications raises concerns about the privacy of data contributors. One robust (from the mathematical point of view) privacy definition is that of Differential Privacy (DP). The peculiarity of DP-based algorithms is that they do not work on anonymized versions of the data; they add a calibrated amount of noise before releasing the results, instead. The goals of this paper are: to give an overview on recent research results marrying DP and neural networks; to present a blueprint for differentially private neural networks; and, to discuss our findings and point out new research challenges.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this case the sensitivity makes usage of the \(L_2\) norm.
- 2.
Anecdotally, when considering more than 4 layers with hundreds of units per layer.
References
Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., Zhang, L.: Deep learning with differential privacy. In: Proceedings of CCS, pp. 308–318. ACM (2016)
Aggarwal, C.C., Philip, S.Y. (eds.): Privacy-Preserving Data Mining. Springer, Heidelberg (2008)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H., et al.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems 19, p. 153 (2007)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Chaudhuri, K., Monteleoni, C.: Privacy-preserving logistic regression. In: Advances in Neural Information Processing Systems, pp. 289–296 (2009)
Cun, Y.L.: Modeles Connexionistes de l’Apprentissage. Ph.D. thesis, Universite’ de Paris (1987)
Dwork, C.: Differential privacy. In: Bugliesi, M., Preneel, B., Sassone, V., Wegener, I. (eds.) ICALP 2006. LNCS, vol. 4052, pp. 1–12. Springer, Heidelberg (2006). https://doi.org/10.1007/11787006_1
Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Dwork, C., Rothblum, G.N., Vadhan, S.: Boosting and differential privacy. In: Proceedings of FOCS, pp. 51–60. IEEE (2010)
Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Kairouz, P., Oh, S., Viswanath, P.: The composition theorem for differential privacy. In: ICML, pp. 1376–1385 (2015)
Kasiviswanathan, S.P., Lee, H.K., Nissim, K., Raskhodnikova, S., Smith, A.: What can we learn privately? SIAM J. Comput. 40(3), 793–826 (2011)
Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. JMLR 10, 1–40 (2009)
LeCun, Y.A., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient BackProp. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 9–48. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_3
Martens, J.: Deep learning via Hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 735–742 (2010)
McSherry, F.D.: Privacy integrated queries: an extensible platform for privacy-preserving data analysis. In: Proceedings of SIGMOD, pp. 19–30. ACM (2009)
Nissim, K., Raskhodnikova, S., Smith, A.: Smooth sensitivity and sampling in private data analysis. In: Proceedings of STOC, pp. 75–84. ACM (2007)
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 30th AAAI Conference on Artificial Intelligence, AAAI, pp. 12–17 (2016)
Rajkumar, A., Agarwal, S.: A differentially private stochastic gradient descent algorithm for multiparty classification. In: International Conference on Artificial Intelligence and Statistics, pp. 933–941 (2012)
Song, S., Chaudhuri, K., Sarwate, A.D.: Stochastic gradient descent with differentially private updates. In: 2013 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 245–248. IEEE (2013)
Zhang, J., Zhang, Z., Xiao, X., Yang, Y., Winslett, M.: Functional mechanism: regression analysis under differential privacy. Proc. VLDB Endow. 5(11), 1364–1375 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Manco, G., Pirrò, G. (2017). Differential Privacy and Neural Networks: A Preliminary Analysis. In: Guidotti, R., Monreale, A., Pedreschi, D., Abiteboul, S. (eds) Personal Analytics and Privacy. An Individual and Collective Perspective. PAP 2017. Lecture Notes in Computer Science(), vol 10708. Springer, Cham. https://doi.org/10.1007/978-3-319-71970-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-71970-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-71969-6
Online ISBN: 978-3-319-71970-2
eBook Packages: Computer ScienceComputer Science (R0)