Private-key fully homomorphic encryption for private classification

DOI10.1007/978-3-319-96418-8_56MaRDI QIDQ1662301zbMATH OpenOpenAlexFDO

Authors A. W. Wood, Vladimir Shpilrain, Kayvan Najarian, Ali Mostashari, Delaram Kahrobaei

Publication date 17 August 2018

Full work available at URL https://doi.org/10.1007/978-3-319-96418-8_56

zbMATH Keywords

machine learningfully homomorphic encryptiondata privacy

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10) Learning and adaptive systems in artificial intelligence (68T05) Medical applications (general) (92C50) Data encryption (aspects in computer science) (68P25)

Recommendations

• Practical private-key fully homomorphic encryption in rings
• Fully homomorphic encryption using ideal lattices
• How to compute on encrypted data
• ML confidential: machine learning on encrypted data
• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks

Cited in

(5)

• SHIELD: Scalable Homomorphic Implementation of Encrypted Data-Classifiers
• Privacy preservation for machine learning training and classification based on homomorphic encryption schemes
• ML confidential: machine learning on encrypted data
• Practical Fully Homomorphic Encryption for Fully Masked Neural Networks
• Secure transfer learning for machine fault diagnosis under different operating conditions

Describes a project that uses

Uses Software

• HElib
• UCI
• gmp

This page was built for publication: Private-key fully homomorphic encryption for private classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1662301)