research-article

NTP-VFL - A New Scheme for Non-3rd Party Vertical Federated Learning

Authors:

Xin JinAuthors Info & Claims

ICMLC '22: Proceedings of the 2022 14th International Conference on Machine Learning and Computing

Pages 134 - 139

https://doi.org/10.1145/3529836.3529841

Published: 21 June 2022 Publication History

Abstract

Vertical Federated Learning (FL) handles decentralized and partitioned vertically data about common entities. While most existing privacy-preserving federated learning algorithms require a third party (TP) as an intermediary data accessor to coordinate model training, we propose a new private-preserving scheme named NTP-VFL (Non-3rd Party Vertical Federated Learning). Utilizing Paillier homomorphic encryption, our algorithm strategy allows for multi-party model training and guarantees clients’ privacy against honest-but-curious adversaries. To the best of our knowledge, this is the first non- TP method that solves multi-party computation problems in Logistic Regression tasks. Our theoretical analysis and extensive experiments show outstanding performance with an average increase in efficiency of about 25% baselines with the traditional federated learning approach.

References

[1]

J. Konecn'y and H.B. McMahan and D. Ramage and P. Richt'arik.:Federated optimization: Distributed machine learning for on-device intelligence.(2016)

[2]

Hardy, S. and Henecka, W. and Ivey-Law, H. and Nock, R. and Patrini, G. and Smith, G. and Thorne, B. Henecka: Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. (2016)

[3]

Wei, Q. and Li, Q. and Zhou, Z. and Ge, Z. Q. and Zhang, Y.: Privacy- preserving two-parties logistic regression on vertically partitioned data using asynchronous gradient sharing. Journal: Peer-to-Peer Networking and Applications,pp.1-9.(2020)

[4]

S. Fienberg, W. Fulp, A. Slavkovic, and T. Wrobel.: Secure log-linear and logistic regression analysis of distributed databases. In: CENEX- SDC Project International Conference, pp. 277–290, Berlin,(2006).

Digital Library

[5]

Chaudhuri, K. and Monteleoni, C.: Privacy-preserving logistic regression. Advances in Neural Information Processing Systems 21, Proceed- ings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, (2008)

[6]

Xie, W. and Wang, Y.and Boker, S. M. and Brown, D. E.:PrivLogit:Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers.(2016)

[7]

Aono, Y. and Hayashi, T. and Phong, L. T. and Wang, L.:Privacy-Preserving Logistic Regression with Distributed Data Sources via Ho- momorphic Encryption.Journal:Ieice Transactions on Information & Systems,E99.D,pp. 2079-2089.(2016)

[8]

Yuval Nardi and Stephen E Fienberg, Robert J Hall.:Achieving both valid and secure logistic regression analysis on aggregated data from different private sources. Journal of Privacy and Confidentiality.(2012)

[9]

PaillierP.:Public-KeyCryptosystemsBasedonCompositeDegreeResid- uosity Classes. In:Advances in Cryptology - EUROCRYPT ’99, Inter- national Conference on the Theory and Application of Cryptographic Techniques,Prague, Czech Republic.Berlin Heidelberg, (1999)

[10]

Cock, M De and Dowsley, R. and Nascimento, Aca and Railsback, D. and Shen, J. and Todoki, A.:High Performance Logistic Regression for Privacy-Preserving Genome Analysis.(2020)

[11]

Khaled El Emam and Saeed Samet and Luk Arbuckle and Robyn Tamblyn and Craig Earle and Murat Kantarcioglu.:A secure distributed logistic regression protocol for the detection of rare adverse drug events. Journal of the American Medical Informatics Association, pp. 453- 461.(2013)

[12]

Mcmahan H B, Moore E, D Ramage, Communication-Efficient Learning of Deep Networks from Decentralized Data[J]. 2016.

[13]

Konen J, Mcmahan H B, Yu F X, Federated Learning: Strategies for Improving Communication Efficiency[J]. 2016.

[14]

Hard A, Rao K, Mathews R, Federated Learning for Mobile Keyboard Prediction[J]. 2018.

[15]

Yuan H, Ma T . Federated Accelerated Stochastic Gradient Descent[J]. arXiv e-prints, 2020.

[16]

Rothchild D, Panda A, Ullah E, FetchSGD: Communication-Efficient Federated Learning with Sketching[J]. 2020.

[17]

Kairouz E, Mcmahan H B . Advances and Open Problems in Federated Learning[J]. Foundations and Trends® in Machine Learning, 2021, 14(1).

[18]

Kim M, Song Y, Shuang W, Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation[J]. JMIR Medical Informatics, 2017, 6(2).

[19]

Cheng K, Fan T, Jin Y, SecureBoost: A Lossless Federated Learning Framework[J]. arXiv, 2019.

[20]

Zhang Q, Wang C, Wu H, GELU-net: a globally encrypted, locally unencrypted deep neural network for privacy-preserved learning[C]// Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18. 2018.

Cited By

Khan Aten Thij MWilbik A(2025)Vertical federated learning: a structured literature reviewKnowledge and Information Systems10.1007/s10115-025-02356-yOnline publication date: 13-Feb-2025
https://doi.org/10.1007/s10115-025-02356-y
Huang YWang WZhao XWang YFeng XHe HYao M(2023)EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third PartyACM Transactions on Knowledge Discovery from Data10.1145/362799318:3(1-20)Online publication date: 9-Dec-2023
https://dl.acm.org/doi/10.1145/3627993
Chen SModi AAgrawal SKhisti A(2023)Quadratic Functional Encryption for Secure Training in Vertical Federated Learning2023 IEEE International Symposium on Information Theory (ISIT)10.1109/ISIT54713.2023.10206955(60-65)Online publication date: 25-Jun-2023
https://doi.org/10.1109/ISIT54713.2023.10206955
Show More Cited By

Recommendations

VFL-R: a novel framework for multi-party in vertical federated learning
Abstract
Federated learning (FL) provides a robust distributed framework for machine learning that solves privacy leakage concerns. In the some cases, it is hard to train the FL model with limited communication sources and low computational capabilities ...
Multi-Party Fair Exchange with an Off-Line Trusted Neutral Party
DEXA '99: Proceedings of the 10th International Workshop on Database & Expert Systems Applications

Recently developed cryptographic techniques [2, 4, 6, 14] make it possible to construct fair exchange protocols with an off-line trusted third party(TTP). The technique is referred to as a verifiable encryption scheme(VES) proves that a ciphertext is ...
SVFL: Secure Vertical Federated Learning on Linear Models
Science of Cyber Security
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 ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMLC '22: Proceedings of the 2022 14th International Conference on Machine Learning and Computing

February 2022

570 pages

ISBN:9781450395700

DOI:10.1145/3529836

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 June 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICMLC 2022

ICMLC 2022: 2022 14th International Conference on Machine Learning and Computing

February 18 - 21, 2022

Guangzhou, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
86
Total Downloads

Downloads (Last 12 months)8
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Khan Aten Thij MWilbik A(2025)Vertical federated learning: a structured literature reviewKnowledge and Information Systems10.1007/s10115-025-02356-yOnline publication date: 13-Feb-2025
https://doi.org/10.1007/s10115-025-02356-y
Huang YWang WZhao XWang YFeng XHe HYao M(2023)EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third PartyACM Transactions on Knowledge Discovery from Data10.1145/362799318:3(1-20)Online publication date: 9-Dec-2023
https://dl.acm.org/doi/10.1145/3627993
Chen SModi AAgrawal SKhisti A(2023)Quadratic Functional Encryption for Secure Training in Vertical Federated Learning2023 IEEE International Symposium on Information Theory (ISIT)10.1109/ISIT54713.2023.10206955(60-65)Online publication date: 25-Jun-2023
https://doi.org/10.1109/ISIT54713.2023.10206955
Mao SZheng XZhang JHu X(2023)PEVLR: A New Privacy-Preserving and Efficient Approach for Vertical Logistic RegressionNeural Information Processing10.1007/978-981-99-8070-3_29(380-392)Online publication date: 20-Nov-2023
https://dl.acm.org/doi/10.1007/978-981-99-8070-3_29

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten