Adjustable Privacy using Autoencoder-based Learning Structure
Not on the map. Why?
Abstract (arXiv)
Inference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets to inference centers in terms of privacy considerations. In this paper, by modifying the structure of the autoencoder, we present a method that manages the utility-privacy trade-off well. To be more precise, the data is first compressed using the encoder, then confidential and non-confidential features are separated and uncorrelated using the classifier. The confidential feature is appropriately combined with noise, and the non-confidential feature is enhanced, and at the end, data with the original data format is produced by the decoder. The proposed architecture also allows data providers to set the level of privacy required for confidential features. The proposed method has been examined for both image and categorical databases, and the results show a significant performance improvement compared to previous methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 7 Apr 2023.
Builds on
22 of 45 references.
References · 22
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016Deep Learning with Differential Privacycited by 2,682
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
- 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
- 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 233
- 2015The Variational Fair Autoencodercited by 223
- 2018Learning Controllable Fair Representationscited by 83
- 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
- 2017A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analyticscited by 30
10 more
- 2018Deep Private-Feature Extractioncited by 30
- 2017Context-Aware Generative Adversarial Privacycited by 27
- 2020TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representationscited by 17
- 2018Convergence Problems with Generative Adversarial Networks (GANs)cited by 14
- 2019Generating Fair Universal Representations using Adversarial Modelscited by 12
- 2020Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep Learningcited by 12
- 2019AutoGAN-based Dimension Reduction for Privacy Preservationcited by 9
- 2022Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformationcited by 5
- 2019Distributed generation of privacy preserving data with user customizationcited by 4
- 2022Decouple-and-Sample: Protecting sensitive information in task agnostic data releasecited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.