English

CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network

Machine Learning 2018-11-06 v1 Machine Learning

Abstract

In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a state of the art performance and won the 2rd place in the non-target task in CAAD 2018.

Keywords

Cite

@article{arxiv.1811.01225,
  title  = {CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network},
  author = {Xiaoyi Dong and Weiming Zhang and Nenghai Yu},
  journal= {arXiv preprint arXiv:1811.01225},
  year   = {2018}
}
R2 v1 2026-06-23T05:03:06.842Z