Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption
Homomorphic encryption (HE) is one of promising cryptographic candidates resolving privacy issues in machine learning on sensitive data such as biomedical data and financial data. However, HE-based solutions commonly suffer from relatively high computational costs due to a large number of iterations...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8444365/ |
| _version_ | 1819169657790136320 |
|---|---|
| author | Jung Hee Cheon Duhyeong Kim Yongdai Kim Yongsoo Song |
| author_facet | Jung Hee Cheon Duhyeong Kim Yongdai Kim Yongsoo Song |
| author_sort | Jung Hee Cheon |
| collection | DOAJ |
| description | Homomorphic encryption (HE) is one of promising cryptographic candidates resolving privacy issues in machine learning on sensitive data such as biomedical data and financial data. However, HE-based solutions commonly suffer from relatively high computational costs due to a large number of iterations in the optimization algorithms such as gradient descent (GD) for the learning phase. In this paper, we propose a new method called ensemble GD for logistic regression, a commonly used machine learning technique for binary classification. Our ensemble method reduces the number of iterations of GD, which results in substantial improvement on the performance of logistic regression based on HE in terms of speed and memory. The convergence of ensemble GD based on HE is guaranteed by our theoretical analysis on the erroneous variant of ensemble GD. We implemented ensemble GD for the logistic regression based on an approximate HE scheme HEAAN on MNIST data set and Credit data set from UCI machine learning repository. Compared to the standard GD for logistic regression, our ensemble method requires only about 60% number of iterations, which results in 60-70% reduction on the running time of total learning procedure in encrypted state, and 30-40% reduction on the storage of encrypted data set. |
| first_indexed | 2024-12-22T19:22:59Z |
| format | Article |
| id | doaj.art-e8a2fde356aa4771a47cd18e3f37b9ca |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T19:22:59Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e8a2fde356aa4771a47cd18e3f37b9ca2022-12-21T18:15:20ZengIEEEIEEE Access2169-35362018-01-016469384694810.1109/ACCESS.2018.28666978444365Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic EncryptionJung Hee Cheon0Duhyeong Kim1https://orcid.org/0000-0002-4766-3456Yongdai Kim2Yongsoo Song3https://orcid.org/0000-0002-0496-9789Department of Mathematical Sciences, Seoul National University, Seoul, South KoreaDepartment of Mathematical Sciences, Seoul National University, Seoul, South KoreaDepartment of Statistics, Seoul National University, Seoul, South KoreaDepartment of Computer Science and Engineering, University of California at San Diego, San Diego, CA, USAHomomorphic encryption (HE) is one of promising cryptographic candidates resolving privacy issues in machine learning on sensitive data such as biomedical data and financial data. However, HE-based solutions commonly suffer from relatively high computational costs due to a large number of iterations in the optimization algorithms such as gradient descent (GD) for the learning phase. In this paper, we propose a new method called ensemble GD for logistic regression, a commonly used machine learning technique for binary classification. Our ensemble method reduces the number of iterations of GD, which results in substantial improvement on the performance of logistic regression based on HE in terms of speed and memory. The convergence of ensemble GD based on HE is guaranteed by our theoretical analysis on the erroneous variant of ensemble GD. We implemented ensemble GD for the logistic regression based on an approximate HE scheme HEAAN on MNIST data set and Credit data set from UCI machine learning repository. Compared to the standard GD for logistic regression, our ensemble method requires only about 60% number of iterations, which results in 60-70% reduction on the running time of total learning procedure in encrypted state, and 30-40% reduction on the storage of encrypted data set.https://ieeexplore.ieee.org/document/8444365/Ensemblegradient descent with errorshomomorphic encryptionprivacy-preserving logistic regression |
| spellingShingle | Jung Hee Cheon Duhyeong Kim Yongdai Kim Yongsoo Song Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption IEEE Access Ensemble gradient descent with errors homomorphic encryption privacy-preserving logistic regression |
| title | Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption |
| title_full | Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption |
| title_fullStr | Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption |
| title_full_unstemmed | Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption |
| title_short | Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption |
| title_sort | ensemble method for privacy preserving logistic regression based on homomorphic encryption |
| topic | Ensemble gradient descent with errors homomorphic encryption privacy-preserving logistic regression |
| url | https://ieeexplore.ieee.org/document/8444365/ |
| work_keys_str_mv | AT jungheecheon ensemblemethodforprivacypreservinglogisticregressionbasedonhomomorphicencryption AT duhyeongkim ensemblemethodforprivacypreservinglogisticregressionbasedonhomomorphicencryption AT yongdaikim ensemblemethodforprivacypreservinglogisticregressionbasedonhomomorphicencryption AT yongsoosong ensemblemethodforprivacypreservinglogisticregressionbasedonhomomorphicencryption |