Context-Aware Generative Adversarial Privacy

Abstract

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called generative adversarial privacy (GAP). GAP leverages recent advancements in generative adversarial networks (GANs) to allow the data holder to learn privatization schemes from the dataset itself. Under GAP, learning the privacy mechanism is formulated as a constrained minimax game between two players: a privatizer that sanitizes the dataset in a way that limits the risk of inference attacks on the individuals' private variables, and an adversary that tries to infer the private variables from the sanitized dataset. To evaluate GAP's performance, we investigate two simple (yet canonical) statistical dataset models: (a) the binary data model; and (b) the binary Gaussian mixture model. For both models, we derive game-theoretically optimal minimax privacy mechanisms, and show that the privacy mechanisms learned from data (in a generative adversarial fashion) match the theoretically optimal ones. This demonstrates that our framework can be easily applied in practice, even in the absence of dataset statistics.

Fundamental Limits of Database Alignment

“…Differential privacy has been widely used to quantifying privacy issues related to databases [2]. More recently, generative adversarial privacy has been proposed [3]. In both cases, if users are present in multiple databases, knowledge of alignment is required to fully apply these frameworks.…”

Defending Against Machine Learning Based Inference Attacks via Adversarial Examples: Opportunities and Challenges

“…Then, they approximately solve the optimization problem using the cluster centroids. Huang et al [58] proposed to use generative adversarial networks to approximately solve the game-theoretic optimization problems. However, these approximate solutions do not have formal guarantees on utility loss of the public data.…”

Mobile sensor data anonymization

“…removing text from images [7]. An optimal privacy mechanism can be formulated as a game between two players, a privatizer and an adversary, with an iterative minimax algorithm [11]. Moreover, the service provider can share a feature extractor based on an initial training set that is then re-trained by the user on their data and then sent back to the service provider [24,30].…”