Advertisement

Efficient Integer Vector Homomorphic Encryption Using Deep Learning for Neural Networks

  • Tianying Xie
  • Yantao LiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11301)

Abstract

Machine learning techniques based on neural networks have achieved significant applications in a wide variety of areas. There is a great risk on disclosing users’ privacy when we train a high-performance model with a large number of datasets collected from users without any protection. To protect user privacy, we propose an Efficient Integer Vector Homomorphic Encryption (EIVHE) scheme using deep learning for neural networks. We use EIVHE to encrypt users’ datasets, then feed the encrypted datasets into a neural network model, and finally obtain the trained model for neural networks. EIVHE is an innovative bridge between cryptography and deep learning, which aims at protecting users’ privacy. The experiments demonstrate that the deep neural networks can be trained by encrypted datasets without privacy leakage, and achieve an accuracy of 89.05% on MNIST. Moreover, this scheme allows us to conduct computation in an efficient and secure way.

Keywords

Deep learning Neural networks Homomorphic encryption MNIST 

References

  1. 1.
    Luo, C., Li, Z., Huang, K., Feng, J., Wang, M.: Zero-shot learning via attribute regression and class prototype rectification. IEEE Trans. Image Process. 27(2), 637–648 (2018)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Hu, G., Peng, X., Yang, Y., Hospedales, T.M., Verbeek, J.: Frankenstein: learning deep face representations using small data. IEEE Trans. Image Process. 27(1), 293–303 (2018)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Zhou, H., Wornell, G.: Efficient homomorphic encryption on integer vectors and its applications. In: 2014 Information Theory and Applications Workshop, pp. 1–9. IEEE Press, New York (2014)Google Scholar
  4. 4.
    Bos, J.W., Lauter, K., Loftus, J., Naehrig, M.: Improved security for a ring-based hully homomorphic encryption scheme. In: Stam, M. (ed.) Cryptography and Coding. LNCS, vol. 8308, pp. 45–64. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-45239-0_4CrossRefGoogle Scholar
  5. 5.
    Fan, J., Vercauteren, F.: Somewhat practical fully homomorphic encryption. Cryptology ePrint Archive, Report 2012/144 (2012)Google Scholar
  6. 6.
    Brakerski, Z., Gentry, C., Vaikuntanathan, V.: (Leveled) fully homomorphic encryption without bootstrapping. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 309–325. ACM, New York (2012)Google Scholar
  7. 7.
    Osia, S.A., et al.: A hybrid deep learning architecture for privacy-preserving mobile analytics. arXiv preprint arXiv:1703.02952 (2018)
  8. 8.
    Rivest, R.L., Adleman, L., Dertouzos, M.L.: On data banks and privacy homomorphisms. Found. Secure Comput. 4(11), 169–180 (1978)MathSciNetGoogle Scholar
  9. 9.
    Rivest, R.L., Shamir, A., Adleman, L.: A method for obtaining digital signatures and public-key cryptosystems. Commun. ACM 21(2), 120–126 (1978)MathSciNetCrossRefGoogle Scholar
  10. 10.
    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).  https://doi.org/10.1007/978-3-540-30576-7_18CrossRefGoogle Scholar
  11. 11.
    Gentry, C.: Fully homomorphic encryption using ideal lattices. In: Proceedings of the Forty-first Annual ACM Symposium on Theory of Computing, pp. 169–178. ACM, New York (2009)Google Scholar
  12. 12.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  13. 13.
    Brakerski, Z., Vaikuntanathan, V.: Efficient fully homomorphic encryption from (standard) LWE. In: 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science, pp. 97–106. IEEE Press, New York (2011)Google Scholar
  14. 14.
    Brakerski, Z., Gentry, C., Halevi, S.: Packed ciphertexts in LWEbased homomorphic encryption. In: Kurosawa, K., Hanaoka, G. (eds.) Public-Key Cryptography - PKC 2013. LNCS, vol. 7778, pp. 1–13. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-36362-7_1CrossRefGoogle Scholar
  15. 15.
    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. ACM, New York (2016)Google Scholar
  16. 16.
    Le, T.P., Aono, Y., Hayashi, T., Wang, L., Moriai, S.: Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans. Inf. Forensics Secur. 13(5), 1333–1345 (2018)CrossRefGoogle Scholar
  17. 17.
    Yang, L., Murmann, B.: Approximate SRAM for energy-efficient, privacy-preserving convolutional neural networks. In: 2017 IEEE Computer Society Annual Symposium on VLSI, pp. 689–694. IEEE Press, New York (2017)Google Scholar
  18. 18.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 448–456. ACM, New York (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of Computer and Information SciencesSouthwest UniversityChongqingChina
  2. 2.College of Computer ScienceChongqing UniversityChongqingChina

Personalised recommendations