# Deep Private-Feature Extraction

arXiv: https://arxiv.org/abs/1802.03151 · HTML: https://mlsanity.com/paper/1802.03151/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2018.

## Built on by (most cited first, 30 of 30)

- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [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)
- [Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach](https://mlsanity.com/paper/2403.01268/) (2024)
- [Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling](https://mlsanity.com/paper/2210.12575/) (2022)
- [A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices](https://mlsanity.com/paper/2304.10020/) (2023)
- [Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition](https://mlsanity.com/paper/2401.14792/) (2024)
- [Learning Robust and Privacy-Preserving Representations via Information Theory](https://mlsanity.com/paper/2412.11066/) (2024)
- [Privacy-Preserving Image Acquisition Using Trainable Optical Kernel](https://mlsanity.com/paper/2106.14577/) (2021)
- [Privacy-Preserving Collaborative Learning through Feature Extraction](https://mlsanity.com/paper/2212.06322/) (2022)
- [Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems](https://mlsanity.com/paper/2307.01292/) (2023)
- [Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks](https://mlsanity.com/paper/2309.02820/) (2023)
- [Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples](https://mlsanity.com/paper/2310.12707/) (2023)
- [The Fundamental Limits of Least-Privilege Learning](https://mlsanity.com/paper/2402.12235/) (2024)
- [Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4](https://mlsanity.com/paper/2404.05047/) (2024)
- [Enabling Inference Privacy with Adaptive Noise Injection](https://mlsanity.com/paper/2104.02261/) (2021)
- [Adjustable Privacy using Autoencoder-based Learning Structure](https://mlsanity.com/paper/2304.03538/) (2023)
- [Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble](https://mlsanity.com/paper/2401.10859/) (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)
- [Selective manipulation of disentangled representations for privacy-aware facial image processing](https://mlsanity.com/paper/2208.12632/) (2022)
- [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)
- [Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations](https://mlsanity.com/paper/2503.09306/) (2025)
- [Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AI](https://mlsanity.com/paper/2505.10942/) (2025)
- [Learning Private Representations through Entropy-based Adversarial Training](https://mlsanity.com/paper/2507.10194/) (2025)
- [InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference](https://mlsanity.com/paper/2511.13365/) (2025)
- [Variational Feature Compression for Model-Specific Representations](https://mlsanity.com/paper/2604.06644/) (2026)
- [Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding](https://mlsanity.com/paper/2608.23382/) (2026)

## Abstract (arXiv)

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy tradeoff. We then implement and evaluate the performance of DPFE on smartphones to understand its complexity, resource demands, and efficiency tradeoffs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive features.