One-time pad system and method for secured and private on-cloud machine learning services

Abstract

An organization's system is configured to label a given document based on an on-cloud classification service, while maintaining confidentiality of the document's content from all entities external to the organization, including: (a) an encoder configured to receive the given document, and to create an embedding of the given document; (b) a deconvolution unit having a neural network, wherein weights of neurons within the neural network are defined relative to a key, the deconvolution unit is configured to receive the embedding, deconvolve the embedding, thereby to create a scrambled document which is then sent to the on-cloud classification service; (c) a pre-trained internal inference network, configured to: (i) receive from the on-cloud service a cloud-classification of the scrambled document, (ii) to also receive a copy of the embedding, and (ii) to identify, given the received cloud-classification and the embedding copy, a true label of the given document.