TY - GEN
T1 - Privacy-Preserving Logistic Regression as a Cloud Service Based on Residue Number System
AU - Cortés-Mendoza, J.M.
AU - Tchernykh, A.
AU - Babenko, M.
AU - Pulido-Gaytán, L.B.
AU - Radchenko, G.
AU - Leprevost, F.
AU - Wang, X.
AU - Avetisyan, A.
N1 - Conference code: 252829
Cited By :1
Export Date: 27 August 2021
Correspondence Address: Tchernykh, A.; CICESE Research CenterMexico; email: chernykh@cicese.edu.mx
Funding details: Russian Foundation for Basic Research, РФФИ, 18-07-01224
Funding text 1: Acknowledgment. This work is partially supported by the Russian Foundation for Basic Research (RFBR), project No. 18-07-01224.
PY - 2020
Y1 - 2020
N2 - The security of data storage, transmission, and processing is emerging as an important consideration in many data analytics techniques and technologies. For instance, in machine learning, the datasets could contain sensitive information that cannot be protected by traditional encryption approaches. Homomorphic encryption schemes and secure multi-party computation are considered as a solution for privacy protection. In this paper, we propose a homomorphic Logistic Regression based on Residue Number System (LR-RNS) that provides security, parallel processing, scalability, error detection, and correction. We verify it using six known datasets from medicine (diabetes, cancer, drugs, etc.) and genomics. We provide experimental analysis with 30 configurations for each dataset to compare the performance and quality of our solution with the state of the art algorithms. For a fair comparison, we use the same 5-fold cross-validation technique. The results show that LR-RNS demonstrates similar accuracy and performance of the classification algorithm at various thresholds settings but with the reduction of training time from 85.9% to 96.1%. © 2020, Springer Nature Switzerland AG.
AB - The security of data storage, transmission, and processing is emerging as an important consideration in many data analytics techniques and technologies. For instance, in machine learning, the datasets could contain sensitive information that cannot be protected by traditional encryption approaches. Homomorphic encryption schemes and secure multi-party computation are considered as a solution for privacy protection. In this paper, we propose a homomorphic Logistic Regression based on Residue Number System (LR-RNS) that provides security, parallel processing, scalability, error detection, and correction. We verify it using six known datasets from medicine (diabetes, cancer, drugs, etc.) and genomics. We provide experimental analysis with 30 configurations for each dataset to compare the performance and quality of our solution with the state of the art algorithms. For a fair comparison, we use the same 5-fold cross-validation technique. The results show that LR-RNS demonstrates similar accuracy and performance of the classification algorithm at various thresholds settings but with the reduction of training time from 85.9% to 96.1%. © 2020, Springer Nature Switzerland AG.
KW - Cloud security
KW - Homomorphic encryption
KW - Logistic regression
KW - Residue number system
KW - Cryptography
KW - Data Analytics
KW - Digital storage
KW - Numbering systems
KW - Privacy by design
KW - Classification algorithm
KW - Cross-validation technique
KW - Experimental analysis
KW - Homomorphic Encryption Schemes
KW - Secure multi-party computation
KW - Sensitive informations
KW - State-of-the-art algorithms
U2 - 10.1007/978-3-030-64616-5_51
DO - 10.1007/978-3-030-64616-5_51
M3 - Conference Paper
SN - 18650929 (ISSN); 9783030646158 (ISBN)
VL - 1331
SP - 598
EP - 610
BT - Russian Supercomputing Days
T2 - 6th Russian Supercomputing Days
Y2 - 21 September 2020 through 22 September 2020
ER -