# Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation

arXiv: https://arxiv.org/abs/2205.01950 · HTML: https://mlsanity.com/paper/2205.01950/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 22 of 22)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data](https://mlsanity.com/paper/2006.11941/) (2020)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Deep Private-Feature Extraction](https://mlsanity.com/paper/1802.03151/) (2018)
- [Learning Privacy Preserving Encodings through Adversarial Training](https://mlsanity.com/paper/1802.05214/) (2018)
- [Context-Aware Generative Adversarial Privacy](https://mlsanity.com/paper/1710.09549/) (2017)
- [VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition](https://mlsanity.com/paper/1803.07100/) (2018)
- [Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization](https://mlsanity.com/paper/1812.10539/) (2018)
- [Generative Adversarial Privacy](https://mlsanity.com/paper/1807.05306/) (2018)
- [Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary](https://mlsanity.com/paper/2102.08308/) (2021)
- [Obfuscation via Information Density Estimation](https://mlsanity.com/paper/1910.08109/) (2019)
- [Distributed generation of privacy preserving data with user customization](https://mlsanity.com/paper/1904.09415/) (2019)
- [K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning](https://mlsanity.com/paper/1805.11640/) (2018)
- [The Utility Cost of Robust Privacy Guarantees](https://mlsanity.com/paper/1801.05926/) (2018)
- [Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest](https://mlsanity.com/paper/1909.12734/) (2019)

## Built on by (most cited first, 5 of 5)

- [Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach](https://mlsanity.com/paper/2309.04427/) (2023)
- [Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4](https://mlsanity.com/paper/2404.05047/) (2024)
- [Adjustable Privacy using Autoencoder-based Learning Structure](https://mlsanity.com/paper/2304.03538/) (2023)
- [Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization](https://mlsanity.com/paper/2404.05043/) (2024)
- [Privacy Enhancement for Gaze Data Using a Noise-Infused Autoencoder](https://mlsanity.com/paper/2508.10918/) (2025)

## Abstract (arXiv)

We propose an adversarial learning framework that deals with the privacy-utility tradeoff problem under two types of conditions: data-type ignorant, and data-type aware. Under data-type aware conditions, the privacy mechanism provides a one-hot encoding of categorical features, representing exactly one class, while under data-type ignorant conditions the categorical variables are represented by a collection of scores, one for each class. We use a neural network architecture consisting of a generator and a discriminator, where the generator consists of an encoder-decoder pair, and the discriminator consists of an adversary and a utility provider. Unlike previous research considering this kind of architecture, which leverages autoencoders (AEs) without introducing any randomness, or variational autoencoders (VAEs) based on learning latent representations which are then forced into a Gaussian assumption, our proposed technique introduces randomness and removes the Gaussian assumption restriction on the latent variables, only focusing on the end-to-end stochastic mapping of the input to privatized data. We test our framework on different datasets: MNIST, FashionMNIST, UCI Adult, and US Census Demographic Data, providing a wide range of possible private and utility attributes. We use multiple adversaries simultaneously to test our privacy mechanism -- some trained from the ground truth data and some trained from the perturbed data generated by our privacy mechanism. Through comparative analysis, our results demonstrate better privacy and utility guarantees than the existing works under similar, data-type ignorant conditions, even when the latter are considered under their original restrictive single-adversary model.