Alert button
Picture for Ian Goodfellow

Ian Goodfellow

Alert button

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Nov 03, 2020
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli

Figure 1 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 2 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 3 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Figure 4 for Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Viaarxiv icon

Creating High Resolution Images with a Latent Adversarial Generator

Mar 04, 2020
David Berthelot, Peyman Milanfar, Ian Goodfellow

Figure 1 for Creating High Resolution Images with a Latent Adversarial Generator
Figure 2 for Creating High Resolution Images with a Latent Adversarial Generator
Figure 3 for Creating High Resolution Images with a Latent Adversarial Generator
Figure 4 for Creating High Resolution Images with a Latent Adversarial Generator
Viaarxiv icon

MixMatch: A Holistic Approach to Semi-Supervised Learning

May 06, 2019
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel

Figure 1 for MixMatch: A Holistic Approach to Semi-Supervised Learning
Figure 2 for MixMatch: A Holistic Approach to Semi-Supervised Learning
Figure 3 for MixMatch: A Holistic Approach to Semi-Supervised Learning
Figure 4 for MixMatch: A Holistic Approach to Semi-Supervised Learning
Viaarxiv icon

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

Mar 22, 2019
Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel

Figure 1 for Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Figure 2 for Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Figure 3 for Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Viaarxiv icon

A Research Agenda: Dynamic Models to Defend Against Correlated Attacks

Mar 14, 2019
Ian Goodfellow

Viaarxiv icon

On Evaluating Adversarial Robustness

Feb 20, 2019
Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Madry, Alexey Kurakin

Viaarxiv icon

New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling

Nov 08, 2018
Ian Goodfellow

Figure 1 for New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
Figure 2 for New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
Viaarxiv icon

Sanity Checks for Saliency Maps

Oct 28, 2018
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim

Figure 1 for Sanity Checks for Saliency Maps
Figure 2 for Sanity Checks for Saliency Maps
Figure 3 for Sanity Checks for Saliency Maps
Figure 4 for Sanity Checks for Saliency Maps
Viaarxiv icon

Discriminator Rejection Sampling

Oct 18, 2018
Samaneh Azadi, Catherine Olsson, Trevor Darrell, Ian Goodfellow, Augustus Odena

Figure 1 for Discriminator Rejection Sampling
Figure 2 for Discriminator Rejection Sampling
Figure 3 for Discriminator Rejection Sampling
Figure 4 for Discriminator Rejection Sampling
Viaarxiv icon