Privacy at a Price: Exploring its Dual Impact on AI Fairness

arXiv:2404.09391v1 Announce Type: cross
Abstract: The worldwide adoption of machine learning (ML) and deep learning models, particularly in critical sectors, such as healthcare and finance, presents substantial challenges in maintaining individual privacy and fairness. These two elements are vital to a trustworthy environment for learning systems. While numerous studies have concentrated on protecting individual privacy through differential privacy (DP) mechanisms, emerging research indicates that differential privacy in machine learning models can unequally impact separate demographic subgroups regarding prediction accuracy. This …

adoption arxiv challenges critical cs.ai cs.cr cs.cy cs.lg deep learning environment fairness finance healthcare impact machine machine learning privacy sectors studies systems