# Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition

arXiv: https://arxiv.org/abs/2401.14792 · HTML: https://mlsanity.com/paper/2401.14792/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 26 Jan 2024.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Deep Private-Feature Extraction](https://mlsanity.com/paper/1802.03151/) (2018)
- [Context-Aware Generative Adversarial Privacy](https://mlsanity.com/paper/1710.09549/) (2017)
- [Privacy-Preserving Adversarial Networks](https://mlsanity.com/paper/1712.07008/) (2017)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [On Perfect Obfuscation: Local Information Geometry Analysis](https://mlsanity.com/paper/2009.04157/) (2020)
- [Variational Leakage: The Role of Information Complexity in Privacy Leakage](https://mlsanity.com/paper/2106.02818/) (2021)

## Built on by (most cited first, 3 of 3)

- [Fundamental Limits of Perfect Concept Erasure](https://mlsanity.com/paper/2503.20098/) (2025)
- [An Efficient Difference-of-Convex Solver for Privacy Funnel](https://mlsanity.com/paper/2403.04778/) (2024)
- [Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition](https://mlsanity.com/paper/2404.02696/) (2024)

## Abstract (arXiv)

In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utility. Both are quantified through the logarithmic loss, a measure also recognized as self-information loss. This exploration deepens the interplay between information-theoretic privacy and representation learning, offering substantive insights into data protection mechanisms for both discriminative and generative models. Importantly, we apply our model to state-of-the-art face recognition systems. The model demonstrates adaptability across diverse inputs, from raw facial images to both derived or refined embeddings, and is competent in tasks such as classification, reconstruction, and generation.