Adversarial Attack with Pattern Replacement
Machine Learning
2019-12-02 v1 Machine Learning
Abstract
We propose a generative model for adversarial attack. The model generates subtle but predictive patterns from the input. To perform an attack, it replaces the patterns of the input with those generated based on examples from some other class. We demonstrate our model by attacking CNN on MNIST.
Cite
@article{arxiv.1911.10875,
title = {Adversarial Attack with Pattern Replacement},
author = {Ziang Dong and Liang Mao and Shiliang Sun},
journal= {arXiv preprint arXiv:1911.10875},
year = {2019}
}