1k citations · 1.7k across the 13 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
stat.ML2018★ 15 cited
Inverting Supervised Representations with Autoregressive Neural Density Models
Charlie Nash, Nate Kushman, Christopher K. I. Williams
We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative in…
cs.LG2018★ 123 cited
Constructing Unrestricted Adversarial Examples with Generative Models
Yang Song, Rui Shu, Nate Kushman +1
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this typ…