51 citations · 99 across the 6 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2020★ 21 cited
Achieving Equalized Odds by Resampling Sensitive Attributes
Yaniv Romano, Stephen Bates, Emmanuel J. Candès
We present a flexible framework for learning predictive models that approximately satisfy the equalized odds notion of fairness. This is achieved by introducing a general discrepan…
stat.ML2018
Adversarial Noise Attacks of Deep Learning Architectures -- Stability Analysis via Sparse Modeled Signals
Yaniv Romano, Aviad Aberdam, Jeremias Sulam +1
Despite their impressive performance, deep convolutional neural networks (CNNs) have been shown to be sensitive to small adversarial perturbations. These nuisances, which one can b…