Abstract
Back-propagation is an effective method for neural network learning. To improve the accuracy of the learning result, in practice multiple parties may want to collaborate by jointly executing the back-propagation algorithm on the union of their respective data sets. During this process no party wants to disclose her/his private data to others for privacy concerns. Existing schemes supporting this kind of collaborative learning just partially solve the problem by limiting the way of data partition or considering only two parties. There still lacks a solution for more general and practical settings wherein two or more parties, each with an arbitrarily partitioned data set, collaboratively conduct learning.
In this paper, by utilizing the power of cloud computing, we solve this open problem with our proposed privacy preserving back-propagation algorithm, which is tailored for the setting of multiparty and arbitrarily partitioned data. In our proposed scheme, each party encrypts his/her private data locally and uploads the ciphertexts into the cloud. The cloud then executes most of the operations pertaining to the learning algorithms with ciphertexts but learns nothing about the original private data. By securely offloading the expensive operations to the cloud, we keep the local computation and communication costs on each party minimal and independent to the number of participants. To support flexible operations over ciphertexts, we adopt and tailor the BGN ‘doubly homomorphic’ encryption algorithm for the multiparty setting. Thorough analysis shows that our proposed scheme is secure, efficient and scalable.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
The health insurance portability and accountability act of privacy and security rules, http://www.hhs.gov/ocr/privacy
National standards to protect the privacy of personal health information, http://www.hhs.gov/ocr/hipaa/finalreg.html
Abramowitz, M., Stegun, I.A.: Handbook of Mathematical Functions: with Formulas, Graphs, and Mathematical Tables. Dover Books on Mathematics. Dover, New York (1964)
Bansal, A., Chen, T., Zhong, S.: Privacy preserving back-propagation neural network learning over arbitrarily partitioned data. Neural Comput. Appl. 20(1), 143–150 (2011)
Boneh, D., Goh, E.-J., Nissim, K.: Evaluating 2-DNF Formulas on Ciphertexts. In: Kilian, J. (ed.) TCC 2005. LNCS, vol. 3378, pp. 325–341. Springer, Heidelberg (2005)
Chen, T., Zhong, S.: Privacy-preserving backpropagation neural network learning. Trans. Neur. Netw. 20(10), 1554–1564 (2009)
Cun, L., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, pp. 396–404. Morgan Kaufmann (1990)
di Vimercati, S.D.C., Foresti, S., Jajodia, S., Paraboschi, S., Samarati, P.: Over-encryption: management of access control evolution on outsourced data. In: Proceedings of the 33rd International Conference on Very Large Data Bases, VLDB 2007, pp. 123–134. VLDB Endowment (2007)
El Gamal, T.: A Public Key Cryptosystem and a Signature Scheme Based on Discrete Logarithms. In: Blakely, G.R., Chaum, D. (eds.) CRYPTO 1984. LNCS, vol. 196, pp. 10–18. Springer, Heidelberg (1985)
Fahlman, S.E.: Faster-learning variations on Back-propagation: An empirical study, pp. 38–51. Morgan Kaufmann (1988)
Flouri, K., Beferull-lozano, B., Tsakalides, P.: Training a svm-based classifier in distributed sensor networks. In: Proceedings of 14nd European Signal Processing Conference, pp. 1–5 (2006)
Grossman, R., Gu, Y.: Data mining using high performance data clouds: experimental studies using sector and sphere. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008, New York, USA, pp. 920–927 (2008)
Grossman, R.L.: The case for cloud computing. IT Professional 11(2), 23–27 (2009)
Law, R.: Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting. Tourism Management 21(4), 331–340 (2000)
Menezes, A.J., Oorschot, P.C.V., Vanstone, S.A., Rivest, R.L.: Handbook of applied cryptography (1997)
Myers, D., Hutchinson, R.: Efficient implementation of piecewise linear activation function for digital vlsi neural networks. Electronics Letters 25(24), 1662–1663 (1989)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Schlitter, N.: A protocol for privacy preserving neural network learning on horizontal partitioned data. In: Proceedings of the Privacy Statistics in Databases (PSD) (September 2008)
Yang, B., Wang, Y.-D., Su, X.-H.: Research and Design of Distributed Neural Networks with Chip Training Algorithm. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005, Part I. LNCS, vol. 3610, pp. 213–216. Springer, Heidelberg (2005)
Yao, A.C.: Protocols for secure computations. In: Proceedings of the 23rd Annual Symposium on Foundations of Computer Science, SFCS 1982, Washington, DC, USA, pp. 160–164 (1982)
Zang, S., Zhong, S.: A privacy-preserving algorithm for distributed training of neural network ensembles. To appear in Neural Computing and Applications
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Yuan, J., Yu, S. (2013). Privacy Preserving Back-Propagation Learning Made Practical with Cloud Computing. In: Keromytis, A.D., Di Pietro, R. (eds) Security and Privacy in Communication Networks. SecureComm 2012. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 106. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36883-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-36883-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36882-0
Online ISBN: 978-3-642-36883-7
eBook Packages: Computer ScienceComputer Science (R0)