Privacy-Preserving Logistic Regression as a Cloud Service Based on Residue Number System

J.M. Cortés-Mendoza, A. Tchernykh, M. Babenko, L.B. Pulido-Gaytán, G. Radchenko, F. Leprevost, X. Wang, A. Avetisyan

    Research output: Conference proceeding/Chapter in Book/Report/Conference Paperpeer-review

    Abstract

    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.
    Original languageEnglish
    Title of host publicationRussian Supercomputing Days
    Subtitle of host publicationRuSCDays 2020
    Pages598-610
    Number of pages13
    Volume1331
    DOIs
    Publication statusPublished - 2020
    Event6th Russian Supercomputing Days - Moscow, Russian Federation
    Duration: 21 Sep 202022 Sep 2020

    Conference

    Conference6th Russian Supercomputing Days
    Abbreviated titleRuSCDays 2020
    Country/TerritoryRussian Federation
    CityMoscow
    Period21/09/2022/09/20

    Keywords

    • Cloud security
    • Homomorphic encryption
    • Logistic regression
    • Residue number system
    • Cryptography
    • Data Analytics
    • Digital storage
    • Numbering systems
    • Privacy by design
    • Classification algorithm
    • Cross-validation technique
    • Experimental analysis
    • Homomorphic Encryption Schemes
    • Secure multi-party computation
    • Sensitive informations
    • State-of-the-art algorithms

    Fingerprint

    Dive into the research topics of 'Privacy-Preserving Logistic Regression as a Cloud Service Based on Residue Number System'. Together they form a unique fingerprint.

    Cite this