Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning

Litong Sun; Runmeng Du; Daojing He; Shanshan Zhu; Rui Wang; Sammy Chan

doi:10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning

Litong Sun, Runmeng Du, Daojing He, Shanshan Zhu, Rui Wang, Sammy Chan

Integral Design & Management

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Data and features often determine the upper limit of results, so that feature engineering is an important stage of federated learning. The existing research schemes all carry out feature engineering based on publicly sharing data. One is plaintext data sharing, the other is ciphertext data sharing, but both types of sharing bring security and efficiency problems. To address these challenges, we propose a feature engineering framework based on Secure Multi-party Computation, which supports multi-party participation in feature engineering and confines feature data locally to ensure data security. Moreover, the computational efficiency of the core algorithm of the framework is also improved compared with the existing methods.

Original language	English
Title of host publication	2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021
Publisher	IEEE
Pages	487-494
Number of pages	8
ISBN (Electronic)	9781665494571
DOIs	https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088
Publication status	Published - 2022
Event	23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021 - Haikou, Hainan, China Duration: 20 Dec 2021 → 22 Dec 2021

Conference

Conference	23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021
Country/Territory	China
City	Haikou, Hainan
Period	20/12/21 → 22/12/21

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Feature Engineering
Federated Learning
Privacy Protection
Secure Multi-party Computation

Access to Document

10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

Feature Engineering Framework based on Secure Multi-Party Computation in Federated LearningFinal published version, 477 KB

Cite this

Sun, L., Du, R., He, D., Zhu, S., Wang, R., & Chan, S. (2022). Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning. In 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021 (pp. 487-494). IEEE. https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

Sun, Litong ; Du, Runmeng ; He, Daojing et al. / Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning. 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021. IEEE, 2022. pp. 487-494

@inproceedings{e75fd7b8189244e29e7ef1e9e5cdbb00,

title = "Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning",

abstract = "Data and features often determine the upper limit of results, so that feature engineering is an important stage of federated learning. The existing research schemes all carry out feature engineering based on publicly sharing data. One is plaintext data sharing, the other is ciphertext data sharing, but both types of sharing bring security and efficiency problems. To address these challenges, we propose a feature engineering framework based on Secure Multi-party Computation, which supports multi-party participation in feature engineering and confines feature data locally to ensure data security. Moreover, the computational efficiency of the core algorithm of the framework is also improved compared with the existing methods.",

keywords = "Feature Engineering, Federated Learning, Privacy Protection, Secure Multi-party Computation",

author = "Litong Sun and Runmeng Du and Daojing He and Shanshan Zhu and Rui Wang and Sammy Chan",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021 ; Conference date: 20-12-2021 Through 22-12-2021",

year = "2022",

doi = "10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088",

language = "English",

pages = "487--494",

booktitle = "2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021",

publisher = "IEEE",

address = "United States",

}

Sun, L, Du, R, He, D, Zhu, S, Wang, R & Chan, S 2022, Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning. in 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021. IEEE, pp. 487-494, 23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021, Haikou, Hainan, China, 20/12/21. https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning. / Sun, Litong; Du, Runmeng; He, Daojing et al.
2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021. IEEE, 2022. p. 487-494.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning

AU - Sun, Litong

AU - Du, Runmeng

AU - He, Daojing

AU - Zhu, Shanshan

AU - Wang, Rui

AU - Chan, Sammy

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - Data and features often determine the upper limit of results, so that feature engineering is an important stage of federated learning. The existing research schemes all carry out feature engineering based on publicly sharing data. One is plaintext data sharing, the other is ciphertext data sharing, but both types of sharing bring security and efficiency problems. To address these challenges, we propose a feature engineering framework based on Secure Multi-party Computation, which supports multi-party participation in feature engineering and confines feature data locally to ensure data security. Moreover, the computational efficiency of the core algorithm of the framework is also improved compared with the existing methods.

AB - Data and features often determine the upper limit of results, so that feature engineering is an important stage of federated learning. The existing research schemes all carry out feature engineering based on publicly sharing data. One is plaintext data sharing, the other is ciphertext data sharing, but both types of sharing bring security and efficiency problems. To address these challenges, we propose a feature engineering framework based on Secure Multi-party Computation, which supports multi-party participation in feature engineering and confines feature data locally to ensure data security. Moreover, the computational efficiency of the core algorithm of the framework is also improved compared with the existing methods.

KW - Feature Engineering

KW - Federated Learning

KW - Privacy Protection

KW - Secure Multi-party Computation

UR - http://www.scopus.com/inward/record.url?scp=85132443676&partnerID=8YFLogxK

U2 - 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

DO - 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

M3 - Conference contribution

AN - SCOPUS:85132443676

SP - 487

EP - 494

BT - 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

PB - IEEE

T2 - 23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

Y2 - 20 December 2021 through 22 December 2021

ER -

Sun L, Du R, He D, Zhu S, Wang R, Chan S. Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning. In 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021. IEEE. 2022. p. 487-494 doi: 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00088

Feature Engineering Framework based on Secure Multi-Party Computation in Federated Learning

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this