This is a kind of machine learning where one wants to train a model or perform inference without transmitting sensitive information.
This information could leak because of data transmission to an untrusted computing server, or because the model itself reveals the structure of its training data (Ateniese et al. 2013; Song et al. 2017).
Bibliography
- Giuseppe Ateniese, Giovanni Felici, Luigi V. Mancini, Angelo Spognardi, Antonio Villani, Domenico Vitali. . "Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers". Arxiv:1306.4447 [cs, Stat]. http://arxiv.org/abs/1306.4447.
- Congzheng Song, Thomas Ristenpart, Vitaly Shmatikov. . "Machine Learning Models That Remember Too Much". Arxiv:1709.07886 [cs]. http://arxiv.org/abs/1709.07886.