# Privacy-Preserving Adversarial Networks

arXiv: https://arxiv.org/abs/1712.07008 · HTML: https://mlsanity.com/paper/1712.07008/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2017.

## Built on by (most cited first, 14 of 14)

- [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)
- [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)
- [Generating gender-ambiguous voices for privacy-preserving speech recognition](https://mlsanity.com/paper/2207.01052/) (2022)
- [Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models](https://mlsanity.com/paper/2407.14960/) (2024)
- [Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs](https://mlsanity.com/paper/2308.13513/) (2023)
- [Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition](https://mlsanity.com/paper/2401.14792/) (2024)
- [Preserving Privacy in GANs Against Membership Inference Attack](https://mlsanity.com/paper/2311.03172/) (2023)
- [Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing](https://mlsanity.com/paper/2202.05833/) (2022)
- [Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition](https://mlsanity.com/paper/2404.02696/) (2024)
- [α-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing](https://mlsanity.com/paper/2310.18241/) (2023)
- [Bayes-Nash Generative Privacy Against Membership Inference Attacks](https://mlsanity.com/paper/2410.07414/) (2024)
- [C-AAE: Compressively Anonymizing Autoencoders for Privacy-Preserving Activity Recognition in Healthcare Sensor Streams](https://mlsanity.com/paper/2507.18072/) (2025)

## Abstract (arXiv)

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive information. Our approach employs adversarially-trained neural networks to implement randomized mechanisms and to perform a variational approximation of mutual information privacy. We validate our Privacy-Preserving Adversarial Networks (PPAN) framework via proof-of-concept experiments on discrete and continuous synthetic data, as well as the MNIST handwritten digits dataset. For synthetic data, our model-agnostic PPAN approach achieves tradeoff points very close to the optimal tradeoffs that are analytically-derived from model knowledge. In experiments with the MNIST data, we visually demonstrate a learned tradeoff between minimizing the pixel-level distortion versus concealing the written digit.