Imitation Privacy
This addresses privacy concerns for users and organizations using machine learning-as-a-service, though it appears incremental as it builds on existing privacy concepts.
The paper tackles the problem of model privacy in cloud-based machine learning services by introducing a general notion called imitation privacy, showing its applicability in query-response and multi-organizational learning scenarios and highlighting its fundamental difference from data-level privacy.
In recent years, there have been many cloud-based machine learning services, where well-trained models are provided to users on a pay-per-query scheme through a prediction API. The emergence of these services motivates this work, where we will develop a general notion of model privacy named imitation privacy. We show the broad applicability of imitation privacy in classical query-response MLaaS scenarios and new multi-organizational learning scenarios. We also exemplify the fundamental difference between imitation privacy and the usual data-level privacy.