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.
@article{arxiv.2009.00442,
title = {Imitation Privacy},
author = {Xun Xian and Xinran Wang and Mingyi Hong and Jie Ding and Reza Ghanadan},
journal= {arXiv preprint arXiv:2009.00442},
year = {2020}
}
Comments
8 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2004.00566