Enhancing privacy in remote data classification

Abstract

Neural networks are a fundamental tool in data classification. A protocol whereby a user may ask a service provider to run a neural network on an input provided in encrypted format is proposed here, in such a way that the neural network owner does not get any knowledge about the processed data. At the same time, the knowledgeb embedded within the network itself is protected.With respect to previousworks in this field, the interaction between the user and the neural network owner is kept to a minimum without resorting to general secure multi-party computation protocols. © 2008 Springer Science+Business Media, LLC.