University of Virginia

2 Posts

Examples of InstaHide scrambling images
University of Virginia

A Privacy Threat Revealed: How researchers cracked InstaHide for computer vision.

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.
Illustration of a doctor and a nurse
University of Virginia

Gender Bender: Double-Hard Debias helps lessen gender bias in NLP models.

AI learns human biases: In word vector space, “man is to computer programmer as woman is to homemaker,” as one paper put it. New research helps language models unlearn such prejudices.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox