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.

Improved version of a paper accepted by Entropy Journal, Special Issue on Information Theory in Machine Learning and Data Science

References in corpus (9)

• RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
• Utility-Privacy Tradeoff in Databases: An Information-theoretic Approach
• Discrete Distribution Estimation under Local Privacy
• Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12
• Scalable Privacy-Preserving Data Sharing Methodology for Genome-Wide Association Studies
• Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
• Managing your Private and Public Data: Bringing down Inference Attacks against your Privacy
• Competitive Privacy in the Smart Grid: An Information-theoretic Approach
• Inference using noisy degrees: Differentially private $\beta$-model and synthetic graphs

Cited by in corpus (12)

• Mobile Sensor Data Anonymization
• Protecting Sensory Data against Sensitive Inferences
• Challenges of Privacy-Preserving Machine Learning in IoT
• An Adversarial Approach to Private Flocking in Mobile Robot Teams
• Constructing dynamic residential energy lifestyles using Latent Dirichlet Allocation
• Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release
• Understanding Compressive Adversarial Privacy
• Variational Leakage: The Role of Information Complexity in Privacy Leakage
• Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
• RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
• Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval
• PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks