Abstract
In this work, we propose an outsourced Secure Multilayer Perceptron (SMLP) scheme where privacy and confidentiality of the data and the model are ensured during its training and the classification phases. More clearly, this SMLP: (i) can be trained by a cloud server based on data previously outsourced by a user in an homomorphically encrypted form; its parameters are homomorphically encrypted giving thus no clues about them to the cloud; and (ii) can also be used for classifying new encrypted data sent by the user while returning him the encrypted classification result. The originality of this scheme is threefold: To the best of our knowledge, it is the first multilayer perceptron (MLP) secured homomorphically in its training phase with no problem of convergence. It does not require extra-communications with the user. And, is based on the Rectified Linear Unit (ReLU) activation function that we secure with no approximation contrarily to actual SMLP solutions. To do so, we take advantage of two semi-honest non-colluding servers. Experimental results carried out on a binary database encrypted with the Paillier cryptosystem demonstrate the overall performance of our scheme and its convergence.
Keywords
- Secure neural network
- Multilayer perceptron
- Homomorphic encryption
- Cloud computing
This work has received a French government support granted to the CominLabs excellence laboratory and managed by the National Research Agency in the “Investing for the Future” program under reference ANR0LABX0701, and to the ANR project INSHARE, ANR15CE1002402.
This is a preview of subscription content, access via your institution.
Buying options
References
Aono, Y., Hayashi, T., Wang, L., Moriai, S., et al.: Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans. Inf. Forensics Secur. 13(5), 1333–1345 (2018)
Bellafqira, R., Coatrieux, G., Bouslimi, D., Quellec, G.: Content-based image retrieval in homomorphic encryption domain. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2944–2947. IEEE (2015)
Bellafqira, R., Coatrieux, G., Bouslimi, D., Quellec, G.: An end to end secure CBIR over encrypted medical database. In: 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), pp. 2537–2540. IEEE (2016)
Bellafqira, R., Coatrieux, G., Bouslimi, D., Quellec, G., Cozic, M.: Proxy re-encryption based on homomorphic encryption. In: Proceedings of the 33rd Annual Computer Security Applications Conference, pp. 154–161. ACM (2017)
Bost, R., Popa, R.A., Tu, S., Goldwasser, S.: Machine learning classification over encrypted data. In: NDSS (2015)
Bouslimi, D., Bellafqira, R., Coatrieux, G.: Data hiding in homomorphically encrypted medical images for verifying their reliability in both encrypted and spatial domains. In: 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), pp. 2496–2499. IEEE (2016)
Castellano, G., Fanelli, A.M.: Variable selection using neural-network models. Neurocomputing 31(1), 1–13 (2000)
Chabanne, H., de Wargny, A., Milgram, J., Morel, C., Prouff, E.: Privacy-preserving classification on deep neural network. IACR Cryptol. ePrint Archive 2017, 35 (2017)
Decencière, E., et al.: TeleOphta: machine learning and image processing methods for teleophthalmology. IRBM 34(2), 196–203 (2013)
Ding, W., Yan, Z., Deng, R.H.: Encrypted data processing with homomorphic re-encryption. Inf. Sci. 409, 35–55 (2017)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Goldreich, O.: Foundations of Cryptography. Basic Applications, vol. 2. Cambridge University Press, New York (2009)
Hsu, C.Y., Lu, C.S., Pei, S.C.: Image feature extraction in encrypted domain with privacy-preserving sift. IEEE Trans. Image Process. 21(11), 4593–4607 (2012)
Huang, Y., Evans, D., Katz, J., Malka, L.: Faster secure two-party computation using garbled circuits. In: USENIX Security Symposium, vol. 201 (2011)
Kerschbaum, F., Biswas, D., de Hoogh, S.: Performance comparison of secure comparison protocols. In: 20th International Workshop on Database and Expert Systems Application, pp. 133–136. IEEE (2009)
Paillier, P.: Public-key cryptosystems based on composite degree residuosity classes. In: Stern, J. (ed.) EUROCRYPT 1999. LNCS, vol. 1592, pp. 223–238. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48910-X_16
Schlitter, N.: A protocol for privacy preserving neural network learning on horizontal partitioned data. In: PSD (2008)
Shokri, R., Shmatikov, V.: Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pp. 1310–1321. ACM (2015)
Veugen, T.: Encrypted integer division. In: 2010 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6. IEEE (2010)
Wu, F., Zhong, H., Shi, R., Huang, H.: Secure two-party computation of the quadratic function’s extreme minimal value. In: 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 2975–2978. IEEE (2012)
Xie, P., Bilenko, M., Finley, T., Gilad-Bachrach, R., Lauter, K., Naehrig, M.: Crypto-nets: Neural networks over encrypted data. arXiv preprint arXiv:1412.6181 (2014)
Zheng, S., et al.: Asynchronous stochastic gradient descent with delay compensation. arXiv preprint arXiv:1609.08326 (2016)
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
Bellafqira, R., Coatrieux, G., Genin, E., Cozic, M. (2019). Secure Multilayer Perceptron Based on Homomorphic Encryption. In: Yoo, C., Shi, YQ., Kim, H., Piva, A., Kim, G. (eds) Digital Forensics and Watermarking. IWDW 2018. Lecture Notes in Computer Science(), vol 11378. Springer, Cham. https://doi.org/10.1007/978-3-030-11389-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-11389-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-11388-9
Online ISBN: 978-3-030-11389-6
eBook Packages: Computer ScienceComputer Science (R0)