Abstract
Privacy-preserving machine learning is a hot topic in Artificial Intelligence (AI) area. However, there are also many security issues in all stages of privacy-oriented machine learning. This paper focuses on the dilemma that the privacy leakage of server-side parameter aggregation and external eavesdropper tampering during message transmission in the distributed machine learning framework. Combining with secret sharing techniques, we present a secure privacy-preserving distributed machine learning protocol under the double-server model based on homomorphic hash function, which enables our protocol verifiable. We also prove that our protocol can meet client semi-honest security requirements. Besides, we evaluate our protocol by comparing with other mainstream privacy preserving frameworks, in the aspects of computation, communication complexity analysis, in addition to a concrete implementation from the perspective of model convergence rate and execution time. Experimental results demonstrate that the local training model tends to converge at nearly 50 epochs where the convergence time is less than 400 s.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bell, J.H., Bonawitz, K.A., Gascón, A., Lepoint, T., Raykova, M.: Secure single-server aggregation with (poly) logarithmic overhead. In: Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security, pp. 1253–1269 (2020)
Bellare, M., Goldreich, O., Goldwasser, S.: Incremental cryptography: the case of hashing and signing. In: Desmedt, Y.G. (ed.) CRYPTO 1994. LNCS, vol. 839, pp. 216–233. Springer, Heidelberg (1994). https://doi.org/10.1007/3-540-48658-5_22
Ben-Or, M., Goldwasser, S., Wigderson, A.: Completeness theorems for non-cryptographic fault-tolerant distributed computation. In: Providing Sound Foundations for Cryptography: On the Work of Shafi Goldwasser and Silvio Micali, pp. 351–371 (2019)
Benaloh, J.C.: Secret sharing homomorphisms: keeping shares of a secret secret (extended abstract). In: Odlyzko, A.M. (ed.) CRYPTO 1986. LNCS, vol. 263, pp. 251–260. Springer, Heidelberg (1987). https://doi.org/10.1007/3-540-47721-7_19
Bonawitz, K., et al.: Practical secure aggregation for federated learning on user-held data. arXiv preprint arXiv:1611.04482 (2016)
Bonawitz, K., et al.: Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 1175–1191 (2017)
Burkhart, M., Strasser, M., Many, D., Dimitropoulos, X.: Sepia: privacy-preserving aggregation of multi-domain network events and statistics. Network 1(101101), 15–32 (2010)
Damgård, I., Pastro, V., Smart, N., Zakarias, S.: Multiparty computation from somewhat homomorphic encryption. In: Safavi-Naini, R., Canetti, R. (eds.) CRYPTO 2012. LNCS, vol. 7417, pp. 643–662. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32009-5_38
Geyer, R.C., Klein, T., Nabi, M.: Differentially private federated learning: a client level perspective. arXiv preprint arXiv:1712.07557 (2017)
Jürgen, S.: A homomorphism theorem for partial algebras. In: Colloquium Mathematicum, vol. 21, pp. 5–21. Institute of Mathematics Polish Academy of Sciences (1970)
Krohn, M.N., Freedman, M.J., Mazieres, D.: On-the-fly verification of rateless erasure codes for efficient content distribution. In: 2004 Proceedings of IEEE Symposium on Security and Privacy, pp. 226–240. IEEE (2004)
Liu, M., Jiang, H., Chen, J., Badokhon, A., Wei, X., Huang, M.C.: A collaborative privacy-preserving deep learning system in distributed mobile environment. In: 2016 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 192–197. IEEE (2016)
Mandal, K., Gong, G.: PriVFL: practical privacy-preserving federated regressions on high-dimensional data over mobile networks. In: Proceedings of the 2019 ACM SIGSAC Conference on Cloud Computing Security Workshop, pp. 57–68 (2019)
Mandal, K., Gong, G., Liu, C.: Nike-based fast privacy-preserving high dimensional data aggregation for mobile devices. Technical report, CACR Technical report, CACR 2018–10, University of Waterloo, Canada (2018)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Nasr, M., Shokri, R., Houmansadr, A.: Comprehensive privacy analysis of deep learning: stand-alone and federated learning under passive and active white-box inference attacks (2018)
Rabin, M.O.: How to exchange secrets with oblivious transfer (2005). http://eprint.iacr.org/2005/187 harvard University Technical Report 81 talr@watson.ibm.com 12955. Accessed 21 June 2005
Rastogi, V., Nath, S.: Differentially private aggregation of distributed time-series with transformation and encryption. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, pp. 735–746 (2010)
Rivest, R.L., Adleman, L., Dertouzos, M.L., et al.: On data banks and privacy homomorphisms. Found. Secur. Comput. 4(11), 169–180 (1978)
Shamir, A.: How to share a secret. Commun. ACM 22(11), 612–613 (1979)
Shokri, R., Shmatikov, V.: Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1310–1321 (2015)
So, J., Guler, B., Avestimehr, A.S.: Turbo-aggregate: breaking the quadratic aggregation barrier in secure federated learning. IEEE J. Sel. Area Inf. Theory. 2, 479–489 (2021)
Yao, A.C.: Protocols for secure computations. In: 23rd Annual Symposium on Foundations of Computer Science (SFCS 1982), pp. 160–164. IEEE (1982)
Yao, A.C.C.: How to generate and exchange secrets. In: 27th Annual Symposium on Foundations of Computer Science (SFCS 1986), pp. 162–167. IEEE (1986)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hong, Y. et al. (2022). A Privacy-Preserving Distributed Machine Learning Protocol Based on Homomorphic Hash Authentication. In: Yuan, X., Bai, G., Alcaraz, C., Majumdar, S. (eds) Network and System Security. NSS 2022. Lecture Notes in Computer Science, vol 13787. Springer, Cham. https://doi.org/10.1007/978-3-031-23020-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-23020-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23019-6
Online ISBN: 978-3-031-23020-2
eBook Packages: Computer ScienceComputer Science (R0)