Generative Adversarial Privacy: A Data-Driven Approach to Information-Theoretic Privacy
Chong Xing Huang, Peter Kairouz, Lalitha Sankar · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · 2018
We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.