# Learning Private Representations through Entropy-based Adversarial Training

arXiv: https://arxiv.org/abs/2507.10194 · HTML: https://mlsanity.com/paper/2507.10194/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 67 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning](https://mlsanity.com/paper/1904.01067/) (2019)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [Investigating Bias and Fairness in Facial Expression Recognition](https://mlsanity.com/paper/2007.10075/) (2020)
- [Guided Variational Autoencoder for Disentanglement Learning](https://mlsanity.com/paper/2004.01255/) (2020)
- [Improving zero-shot learning by mitigating the hubness problem](https://mlsanity.com/paper/1412.6568/) (2014)
- [Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders](https://mlsanity.com/paper/1804.10469/) (2018)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Privacy-Preserving Human Activity Recognition from Extreme Low Resolution](https://mlsanity.com/paper/1604.03196/) (2016)
- [Exploring Disentangled Feature Representation Beyond Face Identification](https://mlsanity.com/paper/1804.03487/) (2018)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Demystifying Inter-Class Disentanglement](https://mlsanity.com/paper/1906.11796/) (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)

## Abstract (arXiv)

How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we introduce a variant of entropy - focal entropy, which mitigates the potential information leakage of the existing entropy-based approaches. We showcase feasibility on multiple benchmarks. The results suggest high target utility at moderate privacy leakage.