Abstract
The amount of data grows exponentially with time and the growth shows no signs of stopping. However, the data in itself is not useful until it can be processed, mined for information and queried. Thus, data sharing is a crucial component of modern computations. On the other hand, exposing the data might lead to serious privacy implications.
In our past research we suggested the use of similitude models, as compact models of data representation instead of the data itself. In this paper we suggest the use of deep neural networks (DNN) as data models to answer different types of queries. In addition, we discuss ownership of the DNN models and how to retain the ownership of the model after sharing it.
We thank the Lynne and William Frankel Center for Computer Science and the Rita Altura Trust Chair in Computer Science.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Laufer, E., Alain, G., Yosinski, J.: Deep generative stochastic networks trainable by backprop. In: ICML (2014)
Bengio, Y., Yao, L., Alain, G., Vincent, P.: Generalized denoising auto-encoders as generative models. In: NIPS (2013)
Creswell, A., Bharath, A.A.: Denoising adversarial autoencoders. IEEE Trans. Neural Netw. Learn. Syst. (2018)
Derbeko, P., Dolev, S., Gudes, E.: Privacy via maintaining small similitude data for big data statistical representation. In: Dinur, I., Dolev, S., Lodha, S. (eds.) CSCML 2018. LNCS, vol. 10879, pp. 105–119. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94147-9_9
Derbeko, P., Dolev, S., Gudes, E., Ullman, J.D.: Efficient and private approximations of distributed databases calculations. In: 2017 IEEE International Conference on Big Data, BigData 2017, Boston, MA, USA, 11–14 December 2017, pp. 4487–4496 (2017)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. In: Fisher, N.I., Sen, P.K. (eds.) The Collected Works of Wassily Hoeffding. Springer Series in Statistics (Perspectives in Statistics). Springer, New York (1962). https://doi.org/10.1007/978-1-4612-0865-5_26
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Kline, S.: Similitude and Approximation Theory. Springer, Heidelberg (1986). https://doi.org/10.1007/978-3-642-61638-9
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2018)
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. CoRR, abs/1511.05644 (2015)
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol. 24, pp. 109–165. Academic Press (1989)
Mohassel, P., Zhang, Y.: SecureML: a system for scalable privacy-preserving machine learning. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 19–38, May 2017
Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. arXiv preprint arXiv:1401.4082 (2014)
Rusu, A.A., et al.: Progressive neural networks. CoRR, abs/1606.04671 (2016)
Seff, A., Beatson, A., Suo, D., Liu, H.: Continual learning in generative adversarial nets. CoRR, abs/1705.08395 (2017)
Serfling, R.J.: Probability inequalities for the sum in sampling without replacement. Ann. Statist. 2(1), 39–48 (1974)
Tassa, T., Gudes, E.: Secure distributed computation of anonymized views of shared databases. ACM Trans. Database Syst. 37(2), 11:1–11:43 (2012)
Yao, A.C.: Protocols for secure computations. In: 2013 IEEE 54th Annual Symposium on Foundations of Computer Science, pp. 160–164 (1982)
Yoshua, B.: Learning deep architectures for AI. Foundations 2, 1–55 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Derbeko, P., Dolev, S., Gudes, E. (2019). MLDStore. In: Dolev, S., Hendler, D., Lodha, S., Yung, M. (eds) Cyber Security Cryptography and Machine Learning. CSCML 2019. Lecture Notes in Computer Science(), vol 11527. Springer, Cham. https://doi.org/10.1007/978-3-030-20951-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-20951-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20950-6
Online ISBN: 978-3-030-20951-3
eBook Packages: Computer ScienceComputer Science (R0)