Privacy-preserving semi-parallel logistic regression training with fully homomorphic encryption

被引:20
|
作者
Carpov, Sergiu [1 ,2 ]
Gama, Nicolas [2 ]
Georgieva, Mariya [2 ,3 ]
Troncoso-Pastoriza, Juan Ramon [3 ]
机构
[1] CEA, LIST, Point Courier 172, F-91191 Gif Sur Yvette, France
[2] Inpher, Innovat Pk A, CH-1015 Lausanne, Switzerland
[3] Ecole Polytech Fed Lausanne, Route Cantonal, CH-1015 Lausanne, Switzerland
关键词
Fully homomorphic encryption; Logistic regression; Genome privacy; Genome-wide association study;
D O I
10.1186/s12920-020-0723-0
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
Background Privacy-preserving computations on genomic data, and more generally on medical data, is a critical path technology for innovative, life-saving research to positively and equally impact the global population. It enables medical research algorithms to be securely deployed in the cloud because operations on encrypted genomic databases are conducted without revealing any individual genomes. Methods for secure computation have shown significant performance improvements over the last several years. However, it is still challenging to apply them on large biomedical datasets. Methods The HE Track of iDash 2018 competition focused on solving an important problem in practical machine learning scenarios, where a data analyst that has trained a regression model (both linear and logistic) with a certain set of features, attempts to find all features in an encrypted database that will improve the quality of the model. Our solution is based on the hybrid framework Chimera that allows for switching between different families of fully homomorphic schemes, namelyTFHEandHEAAN. Results Our solution is one of the finalist of Track 2 of iDash 2018 competition. Among the submitted solutions, ours is the only bootstrapped approach that can be applied for different sets of parameters without re-encrypting the genomic database, making it practical for real-world applications. Conclusions This is the first step towards the more general feature selection problem across large encrypted databases.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Privacy-preserving semi-parallel logistic regression training with fully homomorphic encryption
    Sergiu Carpov
    Nicolas Gama
    Mariya Georgieva
    Juan Ramon Troncoso-Pastoriza
    [J]. BMC Medical Genomics, 13
  • [2] Efficient and Privacy-Preserving Logistic Regression Scheme based on Leveled Fully Homomorphic Encryption
    Liu, Chengjin
    Zoe L Jiang
    Zhao, Xin
    Chen, Qian
    Fang, Junbin
    He, Daojing
    Zhang, Jun
    Wang, Xuan
    [J]. IEEE INFOCOM 2022 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS), 2022,
  • [3] Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption
    Cheon, Jung Hee
    Kim, Duhyeong
    Kim, Yongdai
    Song, Yongsoo
    [J]. IEEE ACCESS, 2018, 6 : 46938 - 46948
  • [4] A privacy-preserving parallel and homomorphic encryption scheme
    Min, Zhaoe
    Yang, Geng
    Shi, Jingqi
    [J]. OPEN PHYSICS, 2017, 15 (01): : 135 - 142
  • [5] Privacy-Preserving Logistic Regression with Distributed Data Sources via Homomorphic Encryption
    Aono, Yoshinori
    Hayashi, Takuya
    Phong, Le Trieu
    Wang, Lihua
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2016, E99D (08): : 2079 - 2089
  • [6] Privacy-Preserving Outsourced Logistic Regression on Encrypted Data from Homomorphic Encryption
    Yu, Xiaopeng
    Zhao, Wei
    Huang, Yunfan
    Ren, Juan
    Tang, Dianhua
    [J]. SECURITY AND COMMUNICATION NETWORKS, 2022, 2022
  • [7] Privacy-preserving genotype imputation with fully homomorphic encryption
    Gursoy, Gamze
    Chielle, Eduardo
    Brannon, Charlotte M.
    Maniatakos, Michail
    Gerstein, Mark
    [J]. CELL SYSTEMS, 2022, 13 (02) : 173 - +
  • [8] On Fully Homomorphic Encryption for Privacy-Preserving Deep Learning
    Hernandez Marcano, Nestor J.
    Moller, Mads
    Hansen, Soren
    Jacobsen, Rune Hylsberg
    [J]. 2019 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2019,
  • [9] Privacy-Preserving Feature Selection with Fully Homomorphic Encryption
    Ono, Shinji
    Takata, Jun
    Kataoka, Masaharu
    Tomohiro, I
    Shin, Kilho
    Sakamoto, Hiroshi
    [J]. ALGORITHMS, 2022, 15 (07)
  • [10] Efficient homomorphic encryption framework for privacy-preserving regression
    Byun, Junyoung
    Park, Saerom
    Choi, Yujin
    Lee, Jaewook
    [J]. APPLIED INTELLIGENCE, 2023, 53 (09) : 10114 - 10129