Transferable Adversarial Perturbations
Wen Zhou, Xin Hou, Yongjun Chen, Mengyun Tang, Xiangqi Huang, Xiang Gan, Yong Yang
Abstract
State-of-the-art deep neural network classifiers are highly vulnerable to adversarial examples which are designed to mislead classifiers with a very small perturbation. However, the performance of black-box attacks (without knowledge of the model parameters) against deployed models always degrades significantly. In this paper, We propose a novel way of perturbations for adversarial examples to enable black-box transfer. We first show that maximizing distance between natural images and their adversarial examples in the intermediate feature maps can improve both white-box attacks (with knowledge of the model parameters) and black-box attacks. We also show that smooth regularization on adversarial perturbations enables transferring across models. Extensive experimental results show that our approach outperforms state-of-the-art methods both in white-box and black-box attacks.
BibTeX
@inproceedings{eccv2018_transferableadve,
title = {Transferable Adversarial Perturbations},
author = {Wen Zhou and Xin Hou and Yongjun Chen and Mengyun Tang and Xiangqi Huang and Xiang Gan and Yong Yang},
booktitle = {ECCV 2018},
year = {2018}
}