DISTRIBUTED MACHINE LEARNING VIA SECURE MULTI-PARTY COMPUTATION AND ENSEMBLE LEARNING

Systems and methods for combining input data and machine learning models that remain secret to each entity are described. This disclosure can allow groups of entities to compute predictions based on datasets that are larger and more detailed collectively than individually, without revealing their data to other parties. This is of particular use in artificial intelligence (AI) tasks in domains which deal with sensitive data, such as medical, financial, or cybersecurity.