# Context-Aware Generative Adversarial Privacy

arXiv: https://arxiv.org/abs/1710.09549 · HTML: https://mlsanity.com/paper/1710.09549/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2017.

## Built on by (most cited first, 27 of 27)

- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks](https://mlsanity.com/paper/2307.10981/) (2023)
- [Noiseless Privacy-Preserving Decentralized Learning](https://mlsanity.com/paper/2404.09536/) (2024)
- [Variational Leakage: The Role of Information Complexity in Privacy Leakage](https://mlsanity.com/paper/2106.02818/) (2021)
- [Unsupervised Information Obfuscation for Split Inference of Neural Networks](https://mlsanity.com/paper/2104.11413/) (2021)
- [Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation](https://mlsanity.com/paper/2205.01950/) (2022)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition](https://mlsanity.com/paper/2401.14792/) (2024)
- [Privacy-Preserving Customer Churn Prediction Model in the Context of Telecommunication Industry](https://mlsanity.com/paper/2411.01447/) (2024)
- [Privacy-Preserving Image Acquisition Using Trainable Optical Kernel](https://mlsanity.com/paper/2106.14577/) (2021)
- [GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservation](https://mlsanity.com/paper/2201.03353/) (2022)
- [Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation](https://mlsanity.com/paper/2201.04782/) (2022)
- [Constructing dynamic residential energy lifestyles using Latent Dirichlet Allocation](https://mlsanity.com/paper/2204.10770/) (2022)
- [Privacy-Aware Adversarial Network in Human Mobility Prediction](https://mlsanity.com/paper/2208.05009/) (2022)
- [RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense](https://mlsanity.com/paper/2304.05135/) (2023)
- [Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4](https://mlsanity.com/paper/2404.05047/) (2024)
- [Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers](https://mlsanity.com/paper/2106.13067/) (2021)
- [On the causality-preservation capabilities of generative modelling](https://mlsanity.com/paper/2301.01109/) (2023)
- [Adjustable Privacy using Autoencoder-based Learning Structure](https://mlsanity.com/paper/2304.03538/) (2023)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [Enabling Privacy-Aware AI-Based Ergonomic Analysis](https://mlsanity.com/paper/2505.07306/) (2025)
- [A Roadmap for Robust End-to-End Alignment](https://mlsanity.com/paper/1809.01036/) (2018)
- [Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization](https://mlsanity.com/paper/2404.05043/) (2024)
- [PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks](https://mlsanity.com/paper/2408.05092/) (2024)
- [SpinML: Customized Synthetic Data Generation for Private Training of Specialized ML Models](https://mlsanity.com/paper/2503.03160/) (2025)
- [Minimax Data Sanitization with Distortion Constraint and Adversarial Inference](https://mlsanity.com/paper/2507.17942/) (2025)

## Abstract (arXiv)

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.