TenSEAL is an open-source library for Privacy-Preserving Machine Learning usingHomomorphic Encryption that can be easily integrated within popular machinelearning frameworks . We benchmark our implementation using MNIST and show that an encrypted convolutional neural network can be evaluated in less than asecond, using less than half a megabyte of communication. We benchmarked our implementation with MNIST . We show thatan encrypted convolutionsal neural .net can be . evaluated in under a second of a megabytes of communication .

Author(s) : Ayoub Benaissa, Bilal Retiat, Bogdan Cebere, Alaa Eddine Belfedhal

Links : PDF - Abstract

Code :

Keywords : encrypted - mnist - tenseal - implementation - neural -

Leave a Reply

Your email address will not be published. Required fields are marked *