Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption

ePrint Report: Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption

Michael Brand, Gaëtan Pradel

Machine learning is a widely-used tool for analysing large datasets, but increasing public demand for privacy preservation and the corresponding introduction of privacy regulations have severely limited what data can be analysed, even when this analysis is for societal benefit.
Homomorphic encryption, which allows computation on encrypted data, is a natural solution to this dilemma, allowing data to be analysed without sacrificing privacy.
Because homomorphic encryption …

analysis brand data datasets demand encryption eprint report fully homomorphic encryption homomorphic encryption introduction large machine machine learning michael practical privacy preservation privacy privacy regulations public regulations report tool