• Publications
  • Influence
Generative Adversarial Nets
TLDR
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model that estimates the probability that a sample came from the training data rather than G. Expand
  • 21,782
  • 4166
  • PDF
Explaining and Harnessing Adversarial Examples
TLDR
A simple and fast method of generating adversarial examples that makes adversarial training practical. Expand
  • 6,877
  • 2010
  • PDF
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TLDR
This paper describes the TensorFlow interface for expressing machine learning algorithms, and an implementation of that interface that we have built at Google. Expand
  • 8,221
  • 934
  • PDF
Intriguing properties of neural networks
TLDR
We find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extend. Expand
  • 6,363
  • 796
  • PDF
Deep Learning
TLDR
Machine-learning technology powers many aspects of modern society: from web searches to content filtering on social networks to recommendations on e-commerce websites, and it is increasingly present in consumer products such as cameras and smartphones. Expand
  • 15,211
  • 702
  • PDF
Improved Techniques for Training GANs
TLDR
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. Expand
  • 4,222
  • 624
  • PDF
Adversarial examples in the physical world
TLDR
Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems even if the adversary has no access to the underlying model. Expand
  • 2,380
  • 469
  • PDF
Generative Adversarial Networks
TLDR
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G. Expand
  • 2,150
  • 386
  • PDF
Deep Learning with Differential Privacy
TLDR
We combine state-of-the-art machine learning methods with advanced privacy-preserving mechanisms, training neural networks within a modest (“single-digit”) privacy budget. Expand
  • 1,569
  • 357
  • PDF
Adversarial Machine Learning at Scale
TLDR
Adversarial examples are malicious inputs designed to fool machine learning models. Expand
  • 1,330
  • 291
  • PDF
...
1
2
3
4
5
...