Data Privacy and Trustworthy Machine Learning

Martin Strobel; Reza Shokri

doi:10.1109/MSEC.2022.3178187

Data Privacy and Trustworthy Machine Learning

Machine Learning 2022-09-15 v1 Cryptography and Security

Authors: Martin Strobel , Reza Shokri

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

The privacy risks of machine learning models is a major concern when training them on sensitive and personal data. We discuss the tradeoffs between data privacy and the remaining goals of trustworthy machine learning (notably, fairness, robustness, and explainability).

Keywords

differential privacy machine learning

Cite

@article{arxiv.2209.06529,
  title  = {Data Privacy and Trustworthy Machine Learning},
  author = {Martin Strobel and Reza Shokri},
  journal= {arXiv preprint arXiv:2209.06529},
  year   = {2022}
}

Comments

Related papers

View all related →

Cryptography and Security · Computer Science

Security and Privacy Considerations for Machine Learning Models Deployed in the Government and Public Sector (white paper)

Nader Sehatbakhsh, Ellie Daw, Onur Savas, Amin Hassanzadeh +1

2020-10-13