Ian Goodfellow

is this you? claim profile

∙ 2 followers
Google ∙ Université de Montréal ∙ OpenAI

Ian J. Goodfellow works as a research scientist in the field of machine learning at Google Brain. He has contributed several times in the field of deep learning.

Goodfellow’s got his B.S. And M.S. And M.S. In computer science, under the leadership of Yoshua Bengio and Aaron Courville, Stanford University and his doctorate in machine learning from the Université de Montréal. Goodfellow joined Google as a member of the Google Brain research team after graduation. He then left Google for the newly established OpenAI Institute. In March 2017, he returned to Google Research.

Goodfellow is known for inventing generative opponent networks, a Facebook approach often used for machine learning. He is also the lead author of the Deep Learning textbook. At Google, it created a system enabling Google Maps to transcribe the addresses of photographs taken by street view cars automatically and showed that machine learning systems are vulnerable to safety.

In 2019, he was listed as a 100 global thinker in Foreign Policy.

Featured Co-authors

Yoshua Bengio
332 publications
Sergey Levine
215 publications
Kyunghyun Cho
157 publications
Pieter Abbeel
155 publications
Xi Chen
144 publications
Trevor Darrell
137 publications
Jun Zhu
116 publications
Aaron Courville
110 publications
Alan Yuille
104 publications
Li Zhang
100 publications
Oriol Vinyals
76 publications

Creating High Resolution Images with a Latent Adversarial Generator

Generating realistic images is difficult, and many formulations for this...
03/04/2020 ∙ by David Berthelot, et al. ∙ 53 ∙ share

read it
MixMatch: A Holistic Approach to Semi-Supervised Learning

Semi-supervised learning has proven to be a powerful paradigm for levera...
05/06/2019 ∙ by David Berthelot, et al. ∙ 20 ∙ share

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

Adversarial examples are inputs to machine learning models designed by a...
03/22/2019 ∙ by Yao Qin, et al. ∙ 40 ∙ share

read it
A Research Agenda: Dynamic Models to Defend Against Correlated Attacks

In this article I describe a research agenda for securing machine learni...
03/14/2019 ∙ by Ian Goodfellow, et al. ∙ 14 ∙ share

read it
On Evaluating Adversarial Robustness

Correctly evaluating defenses against adversarial examples has proven to...
02/18/2019 ∙ by Nicholas Carlini, et al. ∙ 10 ∙ share

read it
New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling

This technical report describes a new feature of the CleverHans library ...
11/08/2018 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it
Discriminator Rejection Sampling

We propose a rejection sampling scheme using the discriminator of a GAN ...
10/16/2018 ∙ by Samaneh Azadi, et al. ∙ 0 ∙ share

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

Explaining the output of a complicated machine learning model like a dee...
10/08/2018 ∙ by Julius Adebayo, et al. ∙ 2 ∙ share

read it
Sanity Checks for Saliency Maps

Saliency methods have emerged as a popular tool to highlight features in...
10/08/2018 ∙ by Julius Adebayo, et al. ∙ 2 ∙ share

read it
Unrestricted Adversarial Examples

We introduce a two-player contest for evaluating the safety and robustne...
09/22/2018 ∙ by Tom B. Brown, et al. ∙ 14 ∙ share

read it
Skill Rating for Generative Models

We explore a new way to evaluate generative models using insights from e...
08/14/2018 ∙ by Catherine Olsson, et al. ∙ 0 ∙ share

read it
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

Machine learning models are notoriously difficult to interpret and debug...
07/28/2018 ∙ by Augustus Odena, et al. ∙ 4 ∙ share

read it
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

Autoencoders provide a powerful framework for learning compressed repres...
07/19/2018 ∙ by David Berthelot, et al. ∙ 10 ∙ share

read it
Motivating the Rules of the Game for Adversarial Example Research

Advances in machine learning have led to broad deployment of systems wit...
07/18/2018 ∙ by Justin Gilmer, et al. ∙ 0 ∙ share

read it
Adversarial Reprogramming of Neural Networks

Deep neural networks are susceptible to adversarial attacks. In computer...
06/28/2018 ∙ by Gamaleldin F. Elsayed, et al. ∙ 10 ∙ share

read it
Defense Against the Dark Arts: An overview of adversarial example security research and future research directions

This article presents a summary of a keynote lecture at the Deep Learnin...
06/11/2018 ∙ by Ian Goodfellow, et al. ∙ 2 ∙ share

read it
Self-Attention Generative Adversarial Networks

In this paper, we propose the Self-Attention Generative Adversarial Netw...
05/21/2018 ∙ by Han Zhang, et al. ∙ 0 ∙ share

read it
Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size

A key problem in research on adversarial examples is that vulnerability ...
04/21/2018 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it
Adversarial Attacks and Defences Competition

To accelerate research on adversarial examples and robustness of machine...
03/31/2018 ∙ by Alexey Kurakin, et al. ∙ 0 ∙ share

read it
Adversarial Logit Pairing

In this paper, we develop improved techniques for defending against adve...
03/16/2018 ∙ by Harini Kannan, et al. ∙ 0 ∙ share

read it
Is Generator Conditioning Causally Related to GAN Performance?

Recent work (Pennington et al, 2017) suggests that controlling the entir...
02/23/2018 ∙ by Augustus Odena, et al. ∙ 0 ∙ share

read it
Adversarial Examples that Fool both Human and Computer Vision

Machine learning models are vulnerable to adversarial examples: small ch...
02/22/2018 ∙ by Gamaleldin F. Elsayed, et al. ∙ 0 ∙ share

read it
MaskGAN: Better Text Generation via Filling in the ______

Neural text generation models are often autoregressive language models o...
01/23/2018 ∙ by William Fedus, et al. ∙ 0 ∙ share

read it
Adversarial Spheres

State of the art computer vision models have been shown to be vulnerable...
01/09/2018 ∙ by Justin Gilmer, et al. ∙ 0 ∙ share

read it
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

Generative adversarial networks (GANs) are a family of generative models...
10/23/2017 ∙ by William Fedus, et al. ∙ 0 ∙ share

read it
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches

The recent, remarkable growth of machine learning has led to intense int...
08/26/2017 ∙ by Martín Abadi, et al. ∙ 0 ∙ share

read it
The Space of Transferable Adversarial Examples

Adversarial examples are maliciously perturbed inputs designed to mislea...
04/11/2017 ∙ by Florian Tramèr, et al. ∙ 0 ∙ share

read it
Adversarial Attacks on Neural Network Policies

Machine learning classifiers are known to be vulnerable to inputs malici...
02/08/2017 ∙ by Sandy Huang, et al. ∙ 0 ∙ share

read it
NIPS 2016 Tutorial: Generative Adversarial Networks

This report summarizes the tutorial presented by the author at NIPS 2016...
12/31/2016 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it
Adversarial Machine Learning at Scale

Adversarial examples are malicious inputs designed to fool machine learn...
11/04/2016 ∙ by Alexey Kurakin, et al. ∙ 0 ∙ share

read it
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Some machine learning applications involve training data that is sensiti...
10/18/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
cleverhans v2.0.0: an adversarial machine learning library

cleverhans is a software library that provides standardized reference im...
10/03/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Adversarial examples in the physical world

Most existing machine learning classifiers are highly vulnerable to adve...
07/08/2016 ∙ by Alexey Kurakin, et al. ∙ 0 ∙ share

read it
Deep Learning with Differential Privacy

Machine learning techniques based on neural networks are achieving remar...
07/01/2016 ∙ by Martín Abadi, et al. ∙ 0 ∙ share

read it
Improved Techniques for Training GANs

We present a variety of new architectural features and training procedur...
06/10/2016 ∙ by Tim Salimans, et al. ∙ 0 ∙ share

read it
Adversarial Training Methods for Semi-Supervised Text Classification

Adversarial training provides a means of regularizing supervised learnin...
05/25/2016 ∙ by Takeru Miyato, et al. ∙ 0 ∙ share

read it
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Many machine learning models are vulnerable to adversarial examples: inp...
05/24/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Unsupervised Learning for Physical Interaction through Video Prediction

A core challenge for an agent learning to interact with the world is to ...
05/23/2016 ∙ by Chelsea Finn, et al. ∙ 0 ∙ share

read it
Theano: A Python framework for fast computation of mathematical expressions

Theano is a Python library that allows to define, optimize, and evaluate...
05/09/2016 ∙ by The Theano Development Team, et al. ∙ 0 ∙ share

read it
Improving the Robustness of Deep Neural Networks via Stability Training

In this paper we address the issue of output instability of deep neural ...
04/15/2016 ∙ by Stephan Zheng, et al. ∙ 0 ∙ share

read it
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

TensorFlow is an interface for expressing machine learning algorithms, a...
03/14/2016 ∙ by Martín Abadi, et al. ∙ 0 ∙ share

read it
Practical Black-Box Attacks against Machine Learning

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vul...
02/08/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Adversarial Autoencoders

In this paper, we propose the "adversarial autoencoder" (AAE), which is ...
11/18/2015 ∙ by Alireza Makhzani, et al. ∙ 0 ∙ share

read it
Net2Net: Accelerating Learning via Knowledge Transfer

We introduce techniques for rapidly transferring the information stored ...
11/18/2015 ∙ by Tianqi Chen, et al. ∙ 0 ∙ share

read it
Efficient Per-Example Gradient Computations

This technical report describes an efficient technique for computing the...
10/07/2015 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it
Intriguing properties of neural networks

Deep neural networks are highly expressive models that have recently ach...
12/21/2013 ∙ by Christian Szegedy, et al. ∙ 0 ∙ share

read it
Joint Training of Deep Boltzmann Machines

We introduce a new method for training deep Boltzmann machines jointly. ...
12/12/2012 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it
Theano: new features and speed improvements

Theano is a linear algebra compiler that optimizes a user's symbolically...
11/23/2012 ∙ by Frédéric Bastien, et al. ∙ 0 ∙ share

read it
Large-Scale Feature Learning With Spike-and-Slab Sparse Coding

We consider the problem of object recognition with a large number of cla...
06/27/2012 ∙ by Ian Goodfellow, et al. ∙ 0 ∙ share

read it