Microsoft Invents A Fast CryptoNet

A CryptoNet is a neural network that works like a standard neural network but with encrypted data. It can make a prediction based on the data without revealing it, or the prediction, to a third party. A CryptoNet is where a neural network meets homomorphic encryption.  The problem that Microsoft Research is trying to solve is how to provide the facilities of a neural as a hosted service – Machine Learning As  a Service MLAS – in a secure way. A potential user might well value the result of applying a neural network to their data but be much less happier about making it visible to a remote server.  There are a few possible ways of keeping the data secure but the most desirable is to use homomorphic encryption. Suppose…


Link to Full Article: Microsoft Invents A Fast CryptoNet