mlsanityData to 14 Oct 2026

Learning Private Representations through Entropy-based Adversarial Training

arXiv 2507.10194 ↗First posted 14 Jul 2025cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

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.

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

40 of 67 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Improved Techniques for Training GANscited by 2,970
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
  8. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  9. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  10. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  11. 2015The Variational Fair Autoencodercited by 223
  12. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
28 more
  1. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  2. 2019On the Fairness of Disentangled Representationscited by 144
  3. 2017Unsupervised Learning of Disentangled Representations from Videocited by 139
  4. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  5. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 122
  6. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  7. 2020Investigating Bias and Fairness in Facial Expression Recognitioncited by 87
  8. 2020Guided Variational Autoencoder for Disentanglement Learningcited by 57
  9. 2014Improving zero-shot learning by mitigating the hubness problemcited by 54
  10. 2018Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoderscited by 49
  11. 2019Mitigating Information Leakage in Image Representations: A Maximum Entropy Approachcited by 48
  12. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  13. 2016Privacy-Preserving Human Activity Recognition from Extreme Low Resolutioncited by 43
  14. 2018Exploring Disentangled Feature Representation Beyond Face Identificationcited by 36
  15. 2019Adversarial Learning of Privacy-Preserving and Task-Oriented Representationscited by 36
  16. 2019Demystifying Inter-Class Disentanglementcited by 31
  17. 2018Deep Private-Feature Extractioncited by 30
  18. 2018Learning Privacy Preserving Encodings through Adversarial Trainingcited by 30
  19. 2019Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?cited by 22
  20. 2022PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANscited by 20
  21. 2016Minimax Filter: Learning to Preserve Privacy from Inference Attackscited by 16
  22. 2017Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryptioncited by 14
  23. 2019On the Global Optima of Kernelized Adversarial Representation Learningcited by 14
  24. 2019Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Imagescited by 13
  25. 2023Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learningcited by 13
  26. 2018Learning Anonymized Representations with Adversarial Neural Networkscited by 7
  27. 2017Privacy-Preserving Deep Inference for Rich User Data on The Cloudcited by 3
  28. 2024Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryptioncited by 3

Built on by

Not cited yet.