Abstract
There is a strong positive correlation between the development of deep learning and the amount of public data available. Not all data can be released in their raw form because of the risk to the privacy of the related individuals. The main objective of privacy-preserving data publication is to anonymize the data while maintaining their utility. In this paper, we propose a privacy-preserving semi-generative adversarial network (PPSGAN) that selectively adds noise to class-independent features of each image to enable the processed image to maintain its original class label. Our experiments on training classifiers with synthetic datasets anonymized with various methods confirm that PPSGAN shows better utility than other conventional methods, including blurring, noise-adding, filtering, and generation using GANs.
Funder
National Research Foundation of Korea
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference55 articles.
1. Meta-Learning for Semi-Supervised Few-Shot Classification;Ren;arXiv,2018
2. One-shot Learning with Memory-Augmented Neural Networks;Santoro;arXiv,2016
3. Zero-Shot Learning Through Cross-Modal Transfer;Socher,2013
4. Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing
5. DPSynthesizer
Cited by
14 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献