Generative Adversarial Privacy
arXiv:1807.05306
Abstract
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.
arXiv commentTalk presentation at Privacy in Machine Learning and Artificial Intelligence (PiMLAI) Workshop, ICML 2018
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Conditional Generative Adversarial Nets
- Utility-Privacy Tradeoff in Databases: An Information-theoretic Approach
- Scalable Privacy-Preserving Data Sharing Methodology for Genome-Wide Association Studies
- Censoring Representations with an Adversary
- Minimax Filter: Learning to Preserve Privacy from Inference Attacks
- DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications
Cited by in corpus (12)
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- AutoGAN-based Dimension Reduction for Privacy Preservation
- Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
- Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
- Obfuscation via Information Density Estimation
- Minimax Rates of Estimating Approximate Differential Privacy
- Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval
- Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
- Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
- Theoretical Guarantees for Model Auditing with Finite Adversaries
- Data-driven Regularized Inference Privacy
- Privacy-Preserving Image Acquisition Using Trainable Optical Kernel