"Shuffling the Deck for Privacy"

A KAUST research team has developed a Machine Learning (ML) approach that addresses a major medical research challenge by integrating an ensemble of privacy-preserving algorithms. The challenge is using the power of Artificial Intelligence (AI) to accelerate genomic data discovery while protecting individuals' privacy. According to KAUST's Xin Gao, omics data typically contains a large amount of private information, such as gene expression and cell composition. This information can often be linked to a person's disease or health status. AI models trained on this data, specifically deep learning models, could retain personal information about individuals. The team seeks to strike a better balance between maintaining privacy and optimizing model performance. This article continues to discuss the ML approach developed by the KAUST team to preserve privacy while analyzing omics data for medical research.

KAUST reports "Shuffling the Deck for Privacy"

Submitted by grigby1