activity
20122022
most citedTheano: new features and speed improvements

1k citations · 2.4k across the 12 of their papers we have counts for

collaborators
Showing 2018Show all

18 papers · 1 filter

cs.CR2018

New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling

Ian Goodfellow

This technical report describes a new feature of the CleverHans library called "attack bundling". Many papers about adversarial examples present lists of error rates corresponding…

cs.CV2018

Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values

Julius Adebayo, Justin Gilmer, Ian Goodfellow +1

Explaining the output of a complicated machine learning model like a deep neural network (DNN) is a central challenge in machine learning. Several proposed local explanation method…

stat.ML2018

Discriminator Rejection Sampling

Samaneh Azadi, Catherine Olsson, Trevor Darrell +2

We propose a rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution. We show that under quite strict assumptio…

cs.CV2018

Sanity Checks for Saliency Maps

Julius Adebayo, Justin Gilmer, Michael Muelly +3

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed…

stat.ML2018

Unrestricted Adversarial Examples

Tom B. Brown, Nicholas Carlini, Chiyuan Zhang +3

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which stud…

stat.ML2018

Skill Rating for Generative Models

Catherine Olsson, Surya Bhupatiraju, Tom Brown +2

We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between genera…