activity
20172020
most citedDistilling a Neural Network Into a Soft Decision Tree

266 citations · 409 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG202015 cited

Deflecting Adversarial Attacks

Yao Qin, Nicholas Frosst, Colin Raffel +2

There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towar…

cs.LG2019

Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions

Yao Qin, Nicholas Frosst, Sara Sabour +3

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or…

stat.ML201932 cited

Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

Nicholas Frosst, Nicolas Papernot, Geoffrey Hinton

We explore and expand the to measure the of class manifolds in representation space: i.e., how close pairs of points f…

cs.CV20187 cited

SMILER: Saliency Model Implementation Library for Experimental Research

Calden Wloka, Toni Kunić, Iuliia Kotseruba +4

The Saliency Model Implementation Library for Experimental Research (SMILER) is a new software package which provides an open, standardized, and extensible framework for maintainin…

cs.LG2018

DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules

Nicholas Frosst, Sara Sabour, Geoffrey Hinton

We present a simple technique that allows capsule models to detect adversarial images. In addition to being trained to classify images, the capsule model is trained to reconstruct…

cs.LG2017266 cited

Distilling a Neural Network Into a Soft Decision Tree

Nicholas Frosst, Geoffrey Hinton

Deep neural networks have proved to be a very effective way to perform classification tasks. They excel when the input data is high dimensional, the relationship between the input…