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

11/03/2018

∙

by   Xiaoyi Dong, et al.

∙

0

∙

share

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.