Distributed Privacy Computing for Protected Data

摘要

This disclosure relates to techniques for developing artificial intelligence algorithms by distributing analytics across multiple sources of privately-coordinated data. In particular, aspects relate to a computer-implemented method comprising: receiving an algorithm and input data requirements associated with the algorithm; identifying data assets as available from a data host based on the input data requirements; Curating the assets into a data storage structure within the infrastructure of the data host, and integrating the algorithm into the secure capsule computing framework. The secure capsule computing framework serves the data assets in the data storage structure to the algorithms in a secure manner that protects the privacy and algorithms of the data assets. The computer implemented method further includes operating the data assets through the algorithm to obtain inferences.