@article{goodfellow_explaining_2015,
title = {Explaining and {Harnessing} {Adversarial} {Examples}},
url = {http://arxiv.org/abs/1412.6572},
abstract = {Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Early attempts at explaining this phenomenon focused on nonlinearity and overfitting. We argue instead that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature. This explanation is supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets. Moreover, this view yields a simple and fast method of generating adversarial examples. Using this approach to provide examples for adversarial training, we reduce the test set error of a maxout network on the MNIST dataset.},
urldate = {2019-11-23},
journal = {arXiv:1412.6572 [cs, stat]},
author = {Goodfellow, Ian J. and Shlens, Jonathon and Szegedy, Christian},
month = mar,
year = {2015},
note = {ZSCC: 0000015
arXiv: 1412.6572},
keywords = {Adversarial attacks, Classical ML, Machine learning}
}
@article{goodfellow_generative_2014,
title = {Generative {Adversarial} {Networks}},
url = {http://arxiv.org/abs/1406.2661},
abstract = {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. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.},
urldate = {2019-11-28},
journal = {arXiv:1406.2661 [cs, stat]},
author = {Goodfellow, Ian J. and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
month = jun,
year = {2014},
note = {ZSCC: 0000010
arXiv: 1406.2661},
keywords = {Adversarial attacks, Classical ML, Implementation, Machine learning}
}