SVFL: Secure Vertical Federated Learning on Linear Models
Pages 332 - 344
Abstract
Federated learning (FL) is a popular technique that enables multiple parties to train a machine learning model collaboratively without disclosing the raw data to each other. A vertically partitioned federated learning configuration is applicable in a variety of real-world scenarios. In this configuration, a comprehensive feature collection is established only when all parties’ datasets are merged and only one party has access to the labels. Existing vertical federated learning strategies for linear models are not very practical, since they involve either a trusted third-party authority (TPA) or heavy communication overheads. To address this issue, this paper proposes SVFL, a secure vertical federated learning framework on linear models, which is based on the Verifiable Inner-Product Computation (VIP) protocol. SVFL enables the secure and private training of linear models, as well as the validation of a malicious server’s computation. In addition, it decreases the number of communication rounds to 3 and is resistant to collusion attacks. Experiments are done on a variety of real-world datasets from the UCI ML repository, and the results demonstrate that SVFL achieves comparable accuracy to conventional linear models.
References
[1]
Abdalla M, Bourse F, De Caro A, and Pointcheval D Katz J Simple functional encryption schemes for inner products Public-Key Cryptography – PKC 2015 2015 Heidelberg Springer 733-751
[2]
Blum, M., Micali, S.: How to generate cryptographically strong sequences of pseudo random bits. In: 23rd Annual Symposium on Foundations of Computer Science (SFCS 1982), pp. 112–117 (1982)
[3]
Bogdanov D, Kamm L, Laur S, and Sokk V Rmind: a tool for cryptographically secure statistical analysis IEEE Trans. Dependable Secure Comput. 2018 15 3 481-495
[4]
Boneh D and Lipton RJ Coppersmith D Quantum cryptanalysis of hidden linear functions Advances in Cryptology — CRYPT0’ 95 1995 Heidelberg Springer 424-437
[5]
Chen, T., Jin, X., Sun, Y., Yin, W.: VAFL: a method of vertical asynchronous federated learning. CoRR abs/2007.06081 (2020). http://arxiv.org/2007.06081
[6]
Corrigan-Gibbs, H., Wolinsky, D.I., Ford, B.: Proactively accountable anonymous messaging in verdict. In: King, S.T. (ed.) Proceedings of the 22th USENIX Security Symposium, Washington, DC, USA, 14–16 August 2013, pp. 147–162. USENIX Association (2013)
[7]
Damgård I and Jurik M Kim K A generalisation, a simplification and some applications of paillier’s probabilistic public-key system Public Key Cryptography 2001 Heidelberg Springer 119-136
[8]
Diffie, W., Hellman, M.E.: New directions in cryptography. In: Democratizing Cryptography (1976)
[9]
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
[10]
European Parliament, Council of the European Union: Regulation (EU) 2016/679 of the European Parliament and of the Council (2016). http://data.europa.eu/eli/reg/2016/679/oj
[11]
Gascón A et al. Secure linear regression on vertically partitioned datasets IACR Cryptol. ePrint Arch. 2016 2016 892
[12]
Hardy, S., et al.: Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR abs/1711.10677 (2017). http://arxiv.org/abs/1711.10677
[13]
Keith, B., 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)
[14]
Krohn, M., Freedman, M., Mazieres, D.: On-the-fly verification of rateless erasure codes for efficient content distribution. In: IEEE Symposium on Security and Privacy, 2004. Proceedings 2004, pp. 226–240 (2004).
[15]
Ma X, Sun X, Wu Y, Liu Z, Chen X, and Dong C Differentially private byzantine-robust federated learning IEEE Trans. Parallel Distrib. Syst. 2022 33 12 3690-3701
[16]
McMahan, H.B., Moore, E., Ramage, D., Arcas, B.A.: Federated learning of deep networks using model averaging. CoRR abs/1602.05629 (2016). http://arxiv.org/abs/1602.05629
[17]
Nikolaenko, V., Weinsberg, U., Ioannidis, S., Joye, M., Boneh, D., Taft, N.: Privacy-preserving ridge regression on hundreds of millions of records. In: 2013 IEEE Symposium on Security and Privacy, pp. 334–348 (2013)
[18]
Wang F, Zhu H, Lu R, Zheng Y, and Li H Achieve efficient and privacy-preserving disease risk assessment over multi-outsourced vertical datasets IEEE Trans. Dependable Secure Comput. 2022 19 3 1492-1504
[19]
Xu, R., Baracaldo, N., Zhou, Y., Anwar, A., Joshi, J., Ludwig, H.: FedV: privacy-preserving federated learning over vertically partitioned data. In: Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security, pp. 181–192. AISec 2021, Association for Computing Machinery, New York, NY, USA (2021)
[20]
Yao, A.C.: Theory and application of trapdoor functions. In: 23rd Annual Symposium on Foundations of Computer Science (SFCS 1982), pp. 80–91 (1982).
[21]
Yao, H., Wang, C., Hai, B., Zhu, S.: Homomorphic hash and blockchain based authentication key exchange protocol for strangers. In: 2018 Sixth International Conference on Advanced Cloud and Big Data (CBD), pp. 243–248 (2018).
Index Terms
- SVFL: Secure Vertical Federated Learning on Linear Models
Index terms have been assigned to the content through auto-classification.
Recommendations
Toward Few-Label Vertical Federated Learning
Federated Learning (FL) provides a novel paradigm for privacy-preserving machine learning, enabling multiple clients to collaborate on model training without sharing private data. To handle multi-source heterogeneous data, Vertical Federated Learning (VFL)...
Label Privacy Source Coding in Vertical Federated Learning
Machine Learning and Knowledge Discovery in Databases. Research TrackAbstractWe study label privacy protection in vertical federated learning (VFL). VFL enables an active party who possesses labeled data to improve model performance (utility) by collaborating with passive parties who have auxiliary features. Recently, ...
An efficient fair UC-secure protocol for two-party computation
With the development of modern Internet and mobile networks, there is an increasing need for collaborative privacy-preserving applications. Secure multi-party computation SMPC gives a general solution to these applications and has become a hot topic. ...
Comments
Information & Contributors
Information
Published In
Jul 2023
525 pages
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 21 November 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Jan 2025