Data Privacy and Trustworthy Machine Learning
arXiv:2209.06529v134 citationsh-index: 44
Originality Synthesis-oriented
AI Analysis
This work tackles privacy concerns for users and organizations deploying ML on sensitive data, but it appears to be a discussion paper without new results, making it incremental.
The paper addresses the privacy risks in machine learning models trained on sensitive data, examining the trade-offs between data privacy and other trustworthiness goals like fairness, robustness, and explainability.
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).