Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples
Ziang Yan, Yiwen Guo, Jian Liang, Changshui Zhang
Abstract
To craft black-box adversarial examples, adversaries need to query the victim model and take proper advantage of its feedback. Existing black-box attacks generally suffer from high query complexity, especially when only the top-1 decision (i.e., the hard-label prediction) of the victim model is available. In this paper, we propose a novel hard-label black-box attack named Policy-Driven Attack, to reduce the query complexity. Our core idea is to learn promising search directions of the adversarial examples using a well-designed policy network in a novel reinforcement learning formulation, in which the queries become more sensible. Experimental results demonstrate that our method can significantly reduce the query complexity in comparison with existing state-of-the-art hard-label black-box attacks on various image classification benchmark datasets. Code and models for reproducing our results are available at https://github.com/ZiangYan/pda.pytorch
BibTeX
@inproceedings{
yan2021policydriven,
title={Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples},
author={Ziang Yan and Yiwen Guo and Jian Liang and Changshui Zhang},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=pzpytjk3Xb2}
}