@inproceedings{d7d1be44b3d24e70a2b1574ae48d1cb5,
title = "Adversarial examples for Chinese text classification",
abstract = "Deep neural networks (DNNs) have been widely adopted in various areas such as image recognition and natural language processing. However, many works show that DNNs for image classification are vulnerable to adversarial examples, which are generated by adding small-magnitude perturbations to the original inputs. In this paper, we show that DNNs for Chinese text classification are also vulnerable to adversarial examples. We propose a marginal attack method to generate adversarial examples that could fool the DNNs. This method adopts the Na{\"i}ve Bayes principle to filter sensitive words and it only adds a small number of sensitive words at the end of the original text. The generated adversarial example could fool a variety of Chinese text classification DNNs, such that the text would be classified to incorrect category with high probability. We conduct extensive experiments to evaluate the attack performance and the results show that the success ratio of the attacks could reach almost 100\% by adding only five sensitive words.",
keywords = "Adversarial Exmaple, Chinese text classification, Deep Learning, Marginal Attack",
author = "Yushun Xie and Zhaoquan Gu and Bin Zhu and Le Wang and Weihong Han and Lihua Yin",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 5th IEEE International Conference on Data Science in Cyberspace, DSC 2020 ; Conference date: 27-07-2020 Through 29-07-2020",
year = "2020",
month = jul,
doi = "10.1109/DSC50466.2020.00043",
language = "英语",
series = "Proceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "238--245",
booktitle = "Proceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020",
address = "美国",
}