mlsanityData to 7 Oct 2026

Deep Private-Feature Extraction

arXiv 1802.03151 ↗First posted 9 Feb 2018stat.ML cs.CR cs.CVcited by 30

Not on the map. Why?

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 5; 2024: 10; 2025: 4; 2026: 2.

30 papers.

Sort:

  1. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  2. 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillationcited by 11
  3. 2021Unsupervised Information Obfuscation for Split Inference of Neural Networkscited by 5
  4. 2022Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformationcited by 5
  5. 2022Decouple-and-Sample: Protecting sensitive information in task agnostic data releasecited by 4
  6. 2022Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Samplingcited by 3
  7. 2023A Survey on Deep Neural Network Partition over Cloud, Edge and End Devicescited by 3
  8. 2024Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognitioncited by 3
  9. 2024Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approachcited by 3
  10. 2024Learning Robust and Privacy-Preserving Representations via Information Theorycited by 3
  11. 2021Privacy-Preserving Image Acquisition Using Trainable Optical Kernelcited by 2
  12. 2022Privacy-Preserving Collaborative Learning through Feature Extractioncited by 2
18 more
  1. 2023Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systemscited by 2
  2. 2023Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Taskscited by 2
  3. 2023Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examplescited by 2
  4. 2024The Fundamental Limits of Least-Privilege Learningcited by 2
  5. 2024Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4cited by 2
  6. 2021Enabling Inference Privacy with Adaptive Noise Injectioncited by 1
  7. 2023Adjustable Privacy using Autoencoder-based Learning Structurecited by 1
  8. 2024Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemblecited by 1
  9. 2024Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognitioncited by 1
  10. 2022Selective manipulation of disentangled representations for privacy-aware facial image processingcited by 0
  11. 2024Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonizationcited by 0
  12. 2024PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networkscited by 0
  13. 2025Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representationscited by 0
  14. 2025Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AIcited by 0
  15. 2025Learning Private Representations through Entropy-based Adversarial Trainingcited by 0
  16. 2025InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inferencecited by 0
  17. 2026Variational Feature Compression for Model-Specific Representationscited by 0
  18. 2026Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encodingcited by 0