作者
Ian Goodfellow
Generative Models
Adversarial Attacks and Defences Competition
Comments 36 pages, 10 figures
Adversarial Logit Pairing
Comments 10 pages
MaskGAN: Better Text Generation via Filling in the______
Comments 16 pages, ICLR 2018
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Comments 18 pages
The Space of Transferable Adversarial Examples
Comments 15 pages, 7 figures
NIPS 2016 Tutorial: Generative Adversarial Networks
Comments v2-v4 are all typo fixes. No substantive changes relative to v1
Practical Black-Box Attacks against Machine Learning
Comments Proceedings of the 2017 ACM Asia Conference on Computer and Communications Security, Abu Dhabi, UAE
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Comments Accepted to ICLR 17 as an oral
Adversarial Machine Learning at Scale
Comments 17 pages, 5 figures
Adversarial examples in the physical world
Comments 14 pages, 6 figures. Demo available at https://youtu.be/zQ_uMenoBCk
Adversarial Attacks on Neural Network Policies
Unsupervised Learning for Physical Interaction through Video Prediction
Comments To appear in NIPS '16; Video results, code, and data available at: http://www.sites.google.com/site/robotprediction
Improved Techniques for Training GANs
Adversarial Autoencoders
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Theano: A Python framework for fast computation of mathematical expressions
Comments 19 pages, 5 figures
Net2Net: Accelerating Learning via Knowledge Transfer
Comments ICLR 2016 submission
Improving the Robustness of Deep Neural Networks via Stability Training
Comments Published in CVPR 2016
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Comments Version 2 updates only the metadata, to correct the formatting of Martín Abadi's name
Efficient Per-Example Gradient Computations
Comments This revision fixed some typos. Many thanks to Hugo Larochelle for reporting them!
Qualitatively characterizing neural network optimization problems
On distinguishability criteria for estimating generative models
Comments This version adds a figure that appeared on the poster at ICLR, changes the template to say that the paper was accepted as a workshop contribution (previously it was under a review as a conference submission), and fixes some typos
Explaining and Harnessing Adversarial Examples
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
On the Challenges of Physical Implementations of RBMs
Journal ref Proc. AAAI 2014, pp. 1199-1205
Generative Adversarial Networks
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
Intriguing properties of neural networks
An empirical analysis of dropout in piecewise linear networks
Comments Extensive updates; 8 pages plus acknowledgements/references
