Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption
Abstract In this manuscript, we develop a multi-party framework tailored for multiple data contributors seeking machine learning insights from combined data sources. Grounded in statistical learning principles, we introduce the Multi-Key Homomorphic Encryption Logistic Regression (MK-HELR) algorithm...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-06-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-63393-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594673197121536 |
|---|---|
| author | David Ha Eun Kang Duhyeong Kim Yongsoo Song Dongwon Lee Hyesun Kwak Brian W. Anthony |
| author_facet | David Ha Eun Kang Duhyeong Kim Yongsoo Song Dongwon Lee Hyesun Kwak Brian W. Anthony |
| author_sort | David Ha Eun Kang |
| collection | DOAJ |
| description | Abstract In this manuscript, we develop a multi-party framework tailored for multiple data contributors seeking machine learning insights from combined data sources. Grounded in statistical learning principles, we introduce the Multi-Key Homomorphic Encryption Logistic Regression (MK-HELR) algorithm, designed to execute logistic regression on encrypted multi-party data. Given that models built on aggregated datasets often demonstrate superior generalization capabilities, our approach offers data contributors the collective strength of shared data while ensuring their original data remains private due to encryption. Apart from facilitating logistic regression on combined encrypted data from diverse sources, this algorithm creates a collaborative learning environment with dynamic membership. Notably, it can seamlessly incorporate new participants during the learning process, addressing the key limitation of prior methods that demanded a predetermined number of contributors to be set before the learning process begins. This flexibility is crucial in real-world scenarios, accommodating varying data contribution timelines and unanticipated fluctuations in participant numbers, due to additions and departures. Using the AI4I public predictive maintenance dataset, we demonstrate the MK-HELR algorithm, setting the stage for further research in secure, dynamic, and collaborative multi-party learning scenarios. |
| format | Article |
| id | doaj-art-18a7e840ac1d4b798baf17bf8b11f8bc |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-18a7e840ac1d4b798baf17bf8b11f8bc2025-01-19T12:24:57ZengNature PortfolioScientific Reports2045-23222024-06-0114111310.1038/s41598-024-63393-1Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryptionDavid Ha Eun Kang0Duhyeong Kim1Yongsoo Song2Dongwon Lee3Hyesun Kwak4Brian W. Anthony5Department of Mechanical Engineering, Massachusetts Institute of TechnologyIntel LabsDepartment of Computer Science and Engineering, Seoul National UniversityDepartment of Computer Science and Engineering, Seoul National UniversityDepartment of Computer Science and Engineering, Seoul National UniversityDepartment of Mechanical Engineering, Massachusetts Institute of TechnologyAbstract In this manuscript, we develop a multi-party framework tailored for multiple data contributors seeking machine learning insights from combined data sources. Grounded in statistical learning principles, we introduce the Multi-Key Homomorphic Encryption Logistic Regression (MK-HELR) algorithm, designed to execute logistic regression on encrypted multi-party data. Given that models built on aggregated datasets often demonstrate superior generalization capabilities, our approach offers data contributors the collective strength of shared data while ensuring their original data remains private due to encryption. Apart from facilitating logistic regression on combined encrypted data from diverse sources, this algorithm creates a collaborative learning environment with dynamic membership. Notably, it can seamlessly incorporate new participants during the learning process, addressing the key limitation of prior methods that demanded a predetermined number of contributors to be set before the learning process begins. This flexibility is crucial in real-world scenarios, accommodating varying data contribution timelines and unanticipated fluctuations in participant numbers, due to additions and departures. Using the AI4I public predictive maintenance dataset, we demonstrate the MK-HELR algorithm, setting the stage for further research in secure, dynamic, and collaborative multi-party learning scenarios.https://doi.org/10.1038/s41598-024-63393-1Statistical learningData privacyMulti-key homomorphic encryptionMulti-party collaborative learningDynamic membershipAdaptive machine learning systems |
| spellingShingle | David Ha Eun Kang Duhyeong Kim Yongsoo Song Dongwon Lee Hyesun Kwak Brian W. Anthony Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption Scientific Reports Statistical learning Data privacy Multi-key homomorphic encryption Multi-party collaborative learning Dynamic membership Adaptive machine learning systems |
| title | Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption |
| title_full | Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption |
| title_fullStr | Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption |
| title_full_unstemmed | Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption |
| title_short | Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption |
| title_sort | harnessing the potential of shared data in a secure inclusive and resilient manner via multi key homomorphic encryption |
| topic | Statistical learning Data privacy Multi-key homomorphic encryption Multi-party collaborative learning Dynamic membership Adaptive machine learning systems |
| url | https://doi.org/10.1038/s41598-024-63393-1 |
| work_keys_str_mv | AT davidhaeunkang harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption AT duhyeongkim harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption AT yongsoosong harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption AT dongwonlee harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption AT hyesunkwak harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption AT brianwanthony harnessingthepotentialofshareddatainasecureinclusiveandresilientmannerviamultikeyhomomorphicencryption |