Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings
Machine Learning
2022-11-14 v2 Cryptography and Security
Abstract
Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organization must assure that sensitive data remains private throughout the whole ML pipeline, i.e., training and inference phases. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data. Thus, organizations can share the data representation to increase machine learning models' performance in scenarios with more than one data source for a shared predictive downstream task.
Cite
@article{arxiv.2211.05717,
title = {Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings},
author = {Ana María Quintero-Ossa and Jesús Solano and Hernán Jarcía and David Zarruk and Alejandro Correa Bahnsen and Carlos Valencia},
journal= {arXiv preprint arXiv:2211.05717},
year = {2022}
}