{Preserving Privacy of Continuous High-dimensional Data with Minimax Filters}
Jihun Hamm · International Conference on Artificial Intelligence and Statistics · 2015
Preserving privacy of high-dimensional and continuous data such as images or biometric data is a challenging problem. This paper formulates this problem as a learning game between three parties: 1) data contributors using a lter to sanitize data samples, 2) a cooperative data aggregator learning a target task using the ltered samples, and 3) an adversary learning to identify contributors using the same ltered samples. Mini