1.5k citations · 5.7k across the 60 of their papers we have counts for
4 papers · 2 filters
On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao +2
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generat…
Editing a classifier by rewriting its prediction rules
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango +3
We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach requires virtually no additional data collection and ca…
Combining Diverse Feature Priors
Saachi Jain, Dimitris Tsipras, Aleksander Madry
To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly. In this work, we explore the design space of le…
Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong, Shibani Santurkar, Aleksander Mądry
We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also bei…