SecureVFL: Privacy-preserving multi-party vertical federated learning based on blockchain and RSS^☆

Abstract

Vertical Federated Learning (VFL), which draws attention because of its ability to evaluate individuals based on features spread across multiple institutions, encounters numerous privacy and security threats. Existing solutions often suffer from centralized architectures, and exorbitant costs. To mitigate these issues, in this paper, we propose SecureVFL, a decentralized multi-party VFL scheme designed to enhance efficiency and trustworthiness while guaranteeing privacy. SecureVFL uses a permissioned blockchain and introduces a novel consensus algorithm, Proof of Feature Sharing (PoFS), to facilitate decentralized, trustworthy, and high-throughput federated training. SecureVFL introduces a verifiable and lightweight three-party Replicated Secret Sharing (RSS) protocol for feature intersection summation among overlapping users. Furthermore, we propose a ??-sharing protocol to achieve federated training in a four-party VFL setting. This protocol involves only addition operations and exhibits robustness. SecureVFL not only enables anonymous interactions among participants but also safeguards their real identities, and provides mechanisms to unmask these identities when malicious activities are performed. We illustrate the proposed mechanism through a case study on VFL across four banks. Finally, our theoretical analysis proves the security of SecureVFL. Experiments demonstrated that SecureVFL outperformed existing multi-party VFL privacy-preserving schemes, such as MP-FedXGB, in terms of both overhead and model performance.

Keywords

Permissioned blockchain / Vertical federated learning / Privacy protection / Replicated secret sharing

CRediT authorship contribution statement

Mochan Fan: Writing - original draft, Methodology, Formal analysis, Conceptualization. Zhipeng Zhang: Formal analysis, Data curation. Zonghang Li: Methodology, Conceptualization. Gang Sun: Writing - review & editing, Supervision, Methodology. Hongfang Yu: Project administration. Jiawen Kang: Writing - review & editing. Mohsen Guizani: Writing - review & editing.

Declaration of Competing Interest

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of the manuscript.

Acknowledgements

This research was supported by Open Research Projects of Zhejiang Lab (No. 2022QA0AB02), Natural Science Foundation of Sichuan Province (2022NSFSC0913), and Sichuan Province Selected Funding for Postdoctoral Research Projects (TB2022032).

References

[1] L. Liu, Y. Zhou, J. Yuan, W. Zhuang, Y. Wang, Economically optimal ms association for multimedia content delivery in cache-enabled heterogeneous cloud radio access networks, IEEE J. Sel. Areas Commun. 37 (7) (2019) 1584-1593.

[2] M. Fan, K. Ji, Z. Zhang, H. Yu, G. Sun, Lightweight privacy and security comput-ing for blockchained federated learning in iot, IEEE Int. Things J. 10 (18) (2023) 16048-16060.

[3] Y.A. Abid, J. Wu, M. Farhan, T. Ahmad, Ecmt framework for Internet of things: an integrative approach employing in-memory attribute examination and sophisti-cated neural network architectures in conjunction with hybridized machine learning methodologies, IEEE Int. Things J. 11 (4) (2023) 5867-5886.

[4] Y. Peng, X. Tang, Y. Zhou, Y. Hou, J. Li, Y. Qi, L. Liu, H. Lin, How to tame mobility in federated learning over mobile networks?, IEEE Trans. Wirel. Commun. 22 (12) (2023) 9640-9657.

[5] M. Fan, K. Ji, Z. Zhang, H. Yu, G. Sun, Lightweight privacy and security comput-ing for blockchained federated learning in iot, IEEE Int. Things J. 10 (18) (2023) 16048-16060.

[6] X. Cao, G. Sun, H. Yu, M. Guizani, Perfed-gan: personalized federated learning via generative adversarial networks, IEEE Int. Things J. 10 (5) (2022) 3749-3762.

[7] Q. Yang, Y. Liu, T. Chen, Y. Tong, Federated machine learning: concept and appli-cations, ACM Trans. Intell. Syst. Technol. 10 (2) (2019) 1-19.

[8] P. Paillier, Public-key cryptosystems based on composite degree residuosity classes, in: International Conference on the Theory and Applications of Cryptographic Tech-niques, Springer, 1999, pp. 223-238.

[9] A. Dalskov, D. Escudero, A. Nof,Fast fully secure multi-party computation over any ring with two-thirds honest majority, in: Proceedings of the 2022 ACM SIGSAC Con-ference on Computer and Communications Security, ACM, 2022, pp. 653-666.

[10] R. Xu, N. Baracaldo, Y. Zhou, A. Anwar, J. Joshi, H. Ludwig,Fedv: privacy-preserving federated learning over vertically partitioned data,in:Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security, ACM, 2021, pp. 181-192.

[11] K. Yang, T. Fan, T. Chen, Y. Shi, Q. Yang, A quasi-Newton method based vertical fed-erated learning framework for logistic regression, arXiv preprint, arXiv :1912.00513, 2019.

[12] C. Asmuth, J. Bloom, A modular approach to key safeguarding, IEEE Trans. Inf. Theory 29 (2) (1983) 208-210.

[13] Y. Wu, S. Cai, X. Xiao, G. Chen, B.C. Ooi, Privacy preserving vertical federated learn-ing for tree-based models, arXiv preprint, arXiv :2008.06170, 2020.

[14] J. Feng, W. Zhang, Q. Pei, J. Wu, X. Lin, Heterogeneous computation and resource allocation for wireless powered federated edge learning systems, IEEE Trans. Com-mun. 70 (5) (2022) 3220-3233.

[15] Y. Huang, X. Feng, W. Wang, H. He, Y. Wang, M. Yao, Efmvfl: an efficient and flexible multi-party vertical federated learning without a third party, ACM Trans. Knowl. Discov. Data 18 (3) (2023) 1-20.

[16] L. Xie, J. Liu, S. Lu, T.H. Chang, Q. Shi, An efficient learning framework for federated xgboost using secret sharing and distributed optimization, ACM Trans. Intell. Syst. Technol. 13 (5) (2022) 1-28.

[17] C.C. Yang, T.Y. Chang, M.S. Hwang, A (t, n) multi-secret sharing scheme, Appl. Math. Comput. 151 (2) (2004) 483-490.

[18] L. Liu, Y. Zhou, W. Zhuang, J. Yuan, L. Tian, Tractable coverage analysis for hexag-onal macrocell-based heterogeneous udns with adaptive interference-aware comp, IEEE Trans. Wirel. Commun. 18 (1) (2018) 503-517.

[19] S. Krenn, T. Lorünser, Verifiable secret sharing, in: An Introduction to Secret Sharing: A Systematic Overview and Guide for Protocol Selection, Springer, 2023, pp. 45-54.

[20] C. Hsu, L. Harn, Z. Xia, M. Zhang,Non-interactive dealer-free dynamic threshold secret sharing based on standard Shamir’s ss for 5g networks, IEEE Access 8 (2020) 203965-203971.

[21] D.C. Leo, A. Polychroniadou, Lightweight, maliciously secure verifiable function se-cret sharing,in: Annual International Conference on the Theory and Applications of Cryptographic Techniques, Springer, 2022, pp. 150-179.

[22] C. Gentry, S. Halevi, V. Lyubashevsky, Practical non-interactive publicly verifiable secret sharing with thousands of parties, in: Annual International Conference on the Theory and Applications of Cryptographic Techniques, Springer, 2022, pp. 458-487.

[23] Y. Dong, W. Hou, X. Chen, S. Zeng, Efficient and secure federated learning based on secret sharing and gradients selection, J. Comput. Res. Dev. 57 (10) (2020) 2241-2250.

[24] Y. Lindell, A. Nof,A framework for constructing fast mpc over arithmetic circuits with malicious adversaries and an honest-majority, in:Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, ACM, 2017, pp. 259-276.

[25] A. Shamir, How to share a secret, Commun. ACM 22 (11) (1979) 612-613.

[26] I. Damgård, C. Orlandi, M. Simkin, Yet another compiler for active security or: ef-ficient mpc over arbitrary rings,in: Annual International Cryptology Conference, Springer, 2018, pp. 799-829.

[27] H. Chaudhari, R. Rachuri, A. Suresh,Trident: efficient 4pc framework for privacy preserving machine learning, arXiv preprint, arXiv :1912.02631, 2019.

[28] X. Ni, X. Xu, L. Lyu, C. Meng, W. Wang, A vertical federated learning framework for graph convolutional network, arXiv preprint, arXiv :2106.11593, 2021.

[29] Y. Zhou, H. Liu, Z. Pan, L. Tian, J. Shi, G. Yang, Two-stage cooperative multicast transmission with optimized power consumption and guaranteed coverage, IEEE J. Sel. Areas Commun. 32 (2) (2013) 274-284.

[30] W. Fang, D. Zhao, J. Tan, C. Chen, C. Yu, L. Wang, L. Wang, J. Zhou, B. Zhang,Large-scale secure xgb for vertical federated learning, in:Proceedings of the 30th ACM International Conference on Information & Knowledge Management, ACM, 2021, pp. 443-452.

[31] W. Ou, J. Zeng, Z. Guo, W. Yan, D. Liu, S. Fuentes, A homomorphic-encryption-based vertical federated learning scheme for rick management, Comput. Sci. Inf. Syst. 17 (3) (2020) 819-834.

[32] D. He, R. Du, S. Zhu, M. Zhang, K. Liang, S. Chan, Secure logistic regression for vertical federated learning, IEEE Internet Comput. 26 (2) (2021) 61-68.

[33] C. Wang, J. Liang, M. Huang, B. Bai, K. Bai, H. Li, Hybrid differentially private federated learning on vertically partitioned data, arXiv preprint, arXiv :2009.02763, 2020.

[34] Q. Li, Z. Wu, Y. Cai,Fedtree: a federated learning system for trees,in:Proceedings of the 6th Machine Learning and Systems Conference, MLSys, 2023, pp. 1-15.

[35] W. Chen, G. Ma, T. Fan, Y. Kang, Q. Xu, Q. Yang, Secureboost+: a high performance gradient boosting tree framework for large scale vertical federated learning, arXiv preprint, arXiv :2110.10927, 2021.

[36] H. Shi, Y. Xu, Y. Jiang, H. Yu, Efficient asynchronous multi-participant vertical fed-erated learning, IEEE Trans. Big Data 10 (6) (2024) 940-952.

[37] L. Luo, J. Feng, H. Yu, G. Sun, Blockchain-enabled two-way auction mechanism for electricity trading in Internet of electric vehicles, IEEE Int. Things J. 9 (11) (2021) 8105-8118.

[38] X. Xu, X. Wang, Z. Li, H. Yu, G. Sun, S. Maharjan, Y. Zhang, Mitigating conflicting transactions in hyperledger fabric-permissioned blockchain for delay-sensitive iot applications, IEEE Int. Things J. 8 (13) (2021) 10596-10607.

[39] A.S. Yahaya, N. Javaid, M.U. Javed, A. Almogren, A. Radwan, Blockchain-based secure energy trading with mutual verifiable fairness in a smart community, IEEE Trans. Ind. Inform. 18 (11) (2022) 7412-7422.

[40] M. Abspoel, A. Dalskov, D. Escudero, A. Nof, An efficient passive-to-active compiler for honest-majority mpc over rings, in: International Conference on Applied Cryp-tography and Network Security, Springer, 2021, pp. 122-152.

[41] W. Cukierski,Give me some credit, https://kaggle.com/competitions/GiveMeSomeCredit, 2023. (Accessed 5 December 2023).

[42] I.C. Yeh, Default of credit card clients, https://archive.ics.uci.edu/dataset/350/default+of+credit+card+clients, 2023. (Accessed 11 December 2023).