Skip to main content

Deep Neural Networks for Encrypted Inference with TFHE

  • Conference paper
  • First Online:
Cyber Security, Cryptology, and Machine Learning (CSCML 2023)

Abstract

Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, neural networks are the dominant machine learning model for unstructured data.

In this work we show how to construct Deep Neural Networks (DNN) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits. We discuss the constraints and show the architecture of DNNs for two computer vision tasks. We benchmark the architectures using the Concrete stack (https://github.com/zama-ai/concrete-ml), an open-source implementation of TFHE.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/zama-ai/concrete-ml/tree/release/0.6.x/use_case_examples.

References

  1. Aharoni, E., et al.: HE-PEx: efficient machine learning under homomorphic encryption using pruning, permutation and expansion. CoRR abs/2207.03384 (2022). https://doi.org/10.48550/arXiv.2207.03384

  2. Albrecht, M.R., Player, R., Scott, S.: On the concrete hardness of learning with errors. Cryptology ePrint Archive, Paper 2015/046 (2015). https://eprint.iacr.org/2015/046

  3. Bergerat, L., et al.: Parameter optimization & larger precision for (T)FHE. Cryptology ePrint Archive, Paper 2022/704 (2022). https://eprint.iacr.org/2022/704

  4. Bos, J.W., Lauter, K., Loftus, J., Naehrig, M.: Improved security for a ring-based fully homomorphic encryption scheme. In: Stam, M. (ed.) IMACC 2013. LNCS, vol. 8308, pp. 45–64. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-45239-0_4

    Chapter  Google Scholar 

  5. Bourse, F., Minelli, M., Minihold, M., Paillier, P.: Fast homomorphic evaluation of deep discretized neural networks. In: Shacham, H., Boldyreva, A. (eds.) CRYPTO 2018. LNCS, vol. 10993, pp. 483–512. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-96878-0_17

    Chapter  Google Scholar 

  6. Brutzkus, A., Gilad-Bachrach, R., Elisha, O.: Low latency privacy preserving inference. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9–15 June 2019, Long Beach, California, USA. Proceedings of Machine Learning Research, vol. 97, pp. 812–821. PMLR (2019). http://proceedings.mlr.press/v97/brutzkus19a.html

  7. Cheon, J.H., Kim, A., Kim, M., Song, Y.: Homomorphic encryption for arithmetic of approximate numbers. In: Takagi, T., Peyrin, T. (eds.) ASIACRYPT 2017. LNCS, vol. 10624, pp. 409–437. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70694-8_15

    Chapter  Google Scholar 

  8. Chillotti, I., Gama, N., Georgieva, M., Izabachène, M.: TFHE: fast fully homomorphic encryption over the torus. J. Cryptol. 33, 34–91 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  9. Chillotti, I., Joye, M., Ligier, D., Orfila, J.B., Tap, S.: CONCRETE: concrete operates on ciphertexts rapidly by extending TFHE. In: WAHC 2020–8th Workshop on Encrypted Computing & Applied Homomorphic Cryptography, vol. 15 (2020)

    Google Scholar 

  10. Chillotti, I., Joye, M., Paillier, P.: Programmable bootstrapping enables efficient homomorphic inference of deep neural networks. IACR Cryptol. ePrint Arch. 2021, 91 (2021)

    Google Scholar 

  11. Folkerts, L., Gouert, C., Tsoutsos, N.G.: REDsec: running encrypted discretized neural networks in seconds. In: Proceedings 2023 Network and Distributed System Security Symposium (2023)

    Google Scholar 

  12. Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K., Naehrig, M., Wernsing, J.: CryptoNets: applying neural networks to encrypted data with high throughput and accuracy. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 201–210. PMLR, New York (2016). https://proceedings.mlr.press/v48/gilad-bachrach16.html

  13. Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2704–2713 (2017)

    Google Scholar 

  14. Joye, M.: Guide to fully homomorphic encryption over the [discretized] torus. Cryptology ePrint Archive, Paper 2021/1402 (2021). https://eprint.iacr.org/2021/1402, https://eprint.iacr.org/2021/1402

  15. Lee, E., et al.: Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 12403–12422. PMLR (2022). https://proceedings.mlr.press/v162/lee22e.html

  16. Lou, Q., Jiang, L.: SHE: a fast and accurate deep neural network for encrypted data. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https://proceedings.neurips.cc/paper/2019/file/56a3107cad6611c8337ee36d178ca129-Paper.pdf

  17. Meyre, A., et al.: Concrete-ML (2022). https://github.com/zama-ai/concrete-ml

  18. Pappalardo, A.: Xilinx/brevitas (2021). https://doi.org/10.5281/zenodo.3333552

  19. Sejnowski, T.J.: The unreasonable effectiveness of deep learning in artificial intelligence. Proc. Natl. Acad. Sci. 117(48), 30033–30038 (2020). https://doi.org/10.1073/pnas.1907373117, https://www.pnas.org/doi/abs/10.1073/pnas.1907373117

  20. Yvinec, E., Dapogny, A., Cord, M., Bailly, K.: SPIQ: data-free per-channel static input quantization. CoRR abs/2203.14642 (2022). https://doi.org/10.48550/arXiv.2203.14642

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Andrei Stoian .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Stoian, A., Frery, J., Bredehoft, R., Montero, L., Kherfallah, C., Chevallier-Mames, B. (2023). Deep Neural Networks for Encrypted Inference with TFHE. In: Dolev, S., Gudes, E., Paillier, P. (eds) Cyber Security, Cryptology, and Machine Learning. CSCML 2023. Lecture Notes in Computer Science, vol 13914. Springer, Cham. https://doi.org/10.1007/978-3-031-34671-2_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-34671-2_34

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-34670-5

  • Online ISBN: 978-3-031-34671-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics