| Title | A New Black Box Attack Generating Adversarial Examples Based on Reinforcement Learning |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Xiao, Wenli, Jiang, Hao, Xia, Song |
| Conference Name | 2020 Information Communication Technologies Conference (ICTC) |
| Keywords | adver-sarial reinforcement learning, adversarial examples, black box attack, Black Box Attacks, composability, Computational modeling, Data models, Deep Neural Network, Gallium nitride, generative adversarial networks, Metrics, Neural networks, pubcrawl, reinforcement learning, Resiliency, Training |
| Abstract | Machine learning can be misled by adversarial examples, which is formed by making small changes to the original data. Nowadays, there are kinds of methods to produce adversarial examples. However, they can not apply non-differentiable models, reduce the amount of calculations, and shorten the sample generation time at the same time. In this paper, we propose a new black box attack generating adversarial examples based on reinforcement learning. By using deep Q-learning network, we can train the substitute model and generate adversarial examples at the same time. Experimental results show that this method only needs 7.7ms to produce an adversarial example, which solves the problems of low efficiency, large amount of calculation and inapplicable to non-differentiable model. |
| DOI | 10.1109/ICTC49638.2020.9123270 |
| Citation Key | xiao_new_2020 |
A New Black Box Attack Generating Adversarial Examples Based on Reinforcement Learning