Data Privacy and Trustworthy Machine Learning

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).

arXiv commentCopyright ©2022, IEEE

References in corpus (4)

• Equality of Opportunity in Supervised Learning
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Privacy Risks of Securing Machine Learning Models against Adversarial Examples
• White-box vs Black-box: Bayes Optimal Strategies for Membership Inference

Cited by in corpus (1)

• Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models