Generative Adversarial Privacy: A Data-Driven Approach to Information-Theoretic Privacy

By Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar, Ram Rajagopal. 2018

44 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Flávio du Pin Calmon
2. Hsiang Hsu
3. Shahab Asoodeh
4. Lalitha Sankar

Citations in the corpus

• Obfuscation via Information Density Estimation (2019, background): “In [2, 3, 11], neural generative models are introduced to generate “privatized” data that resemble the original data.”