Explaining and Harnessing Adversarial Examples


Resource history | v1 (current) | created by janarez

Details

Explaining and Harnessing Adversarial Examples

| created by janarez | Add topic "Adversarial machine learning"
Title
Explaining and Harnessing Adversarial Examples
Type
Paper
Created
2015-03-20
Description
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.
Link
http://arxiv.org/abs/1412.6572
Identifier
no value

authors

This resource has no history of related authors.

topics

resources

This resource has no history of related resources.