HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx models. (arXiv:2302.08260v1 [cs.CR])

Machine learning (ML) algorithms are increasingly important for the success
of products and services, especially considering the growing amount and
availability of data. This also holds for areas handling sensitive data, e.g.
applications processing medical data or facial images. However, people are
reluctant to pass their personal sensitive data to a ML service provider. At
the same time, service providers have a strong interest in protecting their
intellectual property and therefore refrain from publicly sharing their ML
model. Fully homomorphic …

algorithms applications availability data encrypted facial handling images important intellectual property interest machine machine learning medical medical data people personal products protecting sensitive data service service provider service providers services