Andrew Ilyas

FILTER
Selected:

Researchers reduce bias in AI models while preserving or improving accuracy

December 11, 2024

A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.

Using AI to protect against AI image manipulation

July 31, 2023

“PhotoGuard,” developed by MIT CSAIL researchers, prevents unauthorized image manipulation, safeguarding authenticity in the era of advanced generative models.