Skip navigation

A Survey and Guideline on Privacy Enhancing Technologies for Collaborative Machine Learning

There is a growing need to use AI/ML to create valuable information also from data that is sensitive from a privacy perspective. In this paper, we provide a detailed analysis of state of the art for collaborative ML approaches to this problem.

As machine learning and artificial intelligence (ML/AI) are becoming more popular and advanced, there is a wish to turn sensitive data into valuable information through ML/AI techniques revealing only data that is allowed by the parties concerned, or without revealing any information about the data to third parties. Collaborative ML approaches like federated learning (FL) help tackle these needs and concerns, bringing a way to use sensitive data without disclosing critically sensitive features of that data. In this paper, we provide a detailed analysis of state of the art for collaborative ML approaches from a privacy perspective.

 

Full abstract in IEEEXplore DOI: 10.1109/ACCESS.2022.3204037

Authors

Elif Ustundag Soykan, Leyli Karaçay, Ferhat Karakoç, and Emrah Tomur – Ericsson Research

Published in IEEE Access volume 10, Sep 5, 2022.

Open Access under a Creative Commons License.