Papers
Topics
Authors
Recent
Search
2000 character limit reached

SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning based on MKTFHE

Published 17 Nov 2022 in cs.CR and cs.LG | (2211.09353v2)

Abstract: In recent years, distributed machine learning has garnered significant attention. However, privacy continues to be an unresolved issue within this field. Multi-key homomorphic encryption over torus (MKTFHE) is one of the promising candidates for addressing this concern. Nevertheless, there may be security risks in the decryption of MKTFHE. Moreover, to our best known, the latest works about MKTFHE only support Boolean operation and linear operation which cannot directly compute the non-linear function like Sigmoid. Therefore, it is still hard to perform common machine learning such as logistic regression and neural networks in high performance. In this paper, we first discover a possible attack on the existing distributed decryption protocol for MKTFHE and subsequently introduce secret sharing to propose a securer one. Next, we design a new MKTFHE-friendly activation function via \emph{homogenizer} and \emph{compare quads}. Finally, we utilize them to implement logistic regression and neural network training in MKTFHE. Comparing the efficiency and accuracy between using Taylor polynomials of Sigmoid and our proposed function as an activation function, the experiments show that the efficiency of our function is 10 times higher than using 7-order Taylor polynomials straightly and the accuracy of the training model is similar to using a high-order polynomial as an activation function scheme.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. Scalable and secure logistic regression via homomorphic encryption. In Proceedings of the Sixth ACM Conference on Data and Application Security and Privacy, pages 142–144, 2016.
  2. ngraph-he: a graph compiler for deep learning on homomorphically encrypted data. In Proceedings of the 16th ACM International Conference on Computing Frontiers, CF 2019, pages 3–13, 2019.
  3. Fast homomorphic evaluation of deep discretized neural networks. In Advances in Cryptology - CRYPTO 2018, volume 10993 of Lecture Notes in Computer Science, pages 483–512, 2018.
  4. Lattice-based fully dynamic multi-key FHE with short ciphertexts. In Advances in Cryptology - CRYPTO 2016, volume 9814 of Lecture Notes in Computer Science, pages 190–213, 2016.
  5. Ran Canetti. Universally composable security: A new paradigm for cryptographic protocols. In Proceedings 42nd IEEE Symposium on Foundations of Computer Science, pages 136–145. IEEE, 2001.
  6. Multi-key homomorphic encryption from TFHE. In Advances in Cryptology - ASIACRYPT 2019 - 25th International Conference on the Theory and Application of Cryptology and Information Security, volume 11922 of Lecture Notes in Computer Science, pages 446–472, 2019.
  7. Logistic regression over encrypted data from fully homomorphic encryption. IACR Cryptol. ePrint Arch., 2018:462, 2018.
  8. Ensemble method for privacy-preserving logistic regression based on homomorphic encryption. IEEE Access, 6:46938–46948, 2018.
  9. Faster fully homomorphic encryption: Bootstrapping in less than 0.1 seconds. In Advances in Cryptology - ASIACRYPT 2016, volume 10031 of Lecture Notes in Computer Science, pages 3–33, 2016.
  10. Faster packed homomorphic operations and efficient circuit bootstrapping for TFHE. In Advances in Cryptology - ASIACRYPT 2017, volume 10624 of Lecture Notes in Computer Science, pages 377–408. Springer, 2017.
  11. TFHE: fast fully homomorphic encryption over the torus. J. Cryptol., 33(1):34–91, 2020.
  12. Multi-identity and multi-key leveled FHE from learning with errors. In Advances in Cryptology - CRYPTO 2015, volume 9216 of Lecture Notes in Computer Science, pages 630–656, 2015.
  13. CHET: an optimizing compiler for fully-homomorphic neural-network inferencing. In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2019, pages 142–156, 2019.
  14. Aby-a framework for efficient mixed-protocol secure two-party computation. In NDSS, 2015.
  15. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, volume 48 of JMLR Workshop and Conference Proceedings, pages 201–210, 2016.
  16. Preserving model privacy for machine learning in distributed systems. IEEE Transactions on Parallel and Distributed Systems, 29(8):1808–1822, 2018.
  17. Privacy-preserving distributed machine learning made faster. In Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop, pages 1–14, 2023.
  18. Towards round-optimal secure multiparty computations: Multikey fhe without a crs. Cryptology ePrint Archive, Report 2018/1156, 2018. https://ia.cr/2018/1156.
  19. Secure logistic regression based on homomorphic encryption. IACR Cryptol. ePrint Arch., 2018:74, 2018.
  20. On the security of multikey homomorphic encryption. In Cryptography and Coding - 17th IMA International Conference, IMACC 2019, volume 11929 of Lecture Notes in Computer Science, pages 236–251, 2019.
  21. On the computational efficiency of training neural networks. Advances in neural information processing systems, 27, 2014.
  22. On-the-fly multiparty computation on the cloud via multikey fully homomorphic encryption. In Proceedings of the 44th Symposium on Theory of Computing Conference, STOC 2012, pages 1219–1234, 2012.
  23. Pics: Private image classification with svm. IACR Cryptol. ePrint Arch., 2017:1190, 2017.
  24. Secureml: A system for scalable privacy-preserving machine learning. In 2017 IEEE symposium on security and privacy (SP), pages 19–38. IEEE, 2017.
  25. Two round multiparty computation via multi-key FHE. In Advances in Cryptology - EUROCRYPT 2016, volume 9666 of Lecture Notes in Computer Science, pages 735–763, 2016.
  26. Two round multiparty computation via multi-key fhe. In Annual International Conference on the Theory and Applications of Cryptographic Techniques, pages 735–763, 2016.
  27. Multi-key FHE from lwe, revisited. In Theory of Cryptography - 14th International Conference, TCC 2016-B, volume 9986 of Lecture Notes in Computer Science, pages 217–238, 2016.
  28. Low-latency privacy-preserving outsourcing of deep neural network inference. IEEE Internet Things J., 8(5):3300–3309, 2021.
  29. Scikit-learn: Machine learning without learning the machinery. GetMobile: Mobile Computing and Communications, 19(1):29–33, 2015.
  30. A survey on distributed machine learning. ACM Computing Surveys (CSUR), 53(2):1–33, 2020.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up