COLING 2022main3 citations

PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack

Rui Zheng, Rong Bao, Qin Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu

Abstract

Adversarial training, which minimizes the loss of adversarially perturbed examples, has received considerable attention. However, these methods require modifying all model parameters and optimizing the model from scratch, which is parameter inefficient and unfriendly to the already deployed models. As an alternative, we propose a pluggable defense module PlugAT, to provide robust predictions by adding a few trainable parameters to the model inputs while keeping the original model frozen. To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones. The PlugAT-equipped BERT model substantially improves robustness over several strong baselines on various text classification tasks, whilst training only 9.1% parameters. We observe that defense modules trained under the same model architecture have domain adaptation ability between similar text classification datasets.

BibTeX
@inproceedings{zheng-etal-2022-plugat,
    title = "{P}lug{AT}: A Plug and Play Module to Defend against Textual Adversarial Attack",
    author = "Zheng, Rui  and
      Bao, Rong  and
      Liu, Qin  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing  and
      Xie, Rui  and
      Wu, Wei",
    editor = "Calzolari, Nicoletta  and
      Huang, Chu-Ren  and
      Kim, Hansaem  and
      Pustejovsky, James  and
      Wanner, Leo  and
      Choi, Key-Sun  and
      Ryu, Pum-Mo  and
      Chen, Hsin-Hsi  and
      Donatelli, Lucia  and
      Ji, Heng  and
      Kurohashi, Sadao  and
      Paggio, Patrizia  and
      Xue, Nianwen  and
      Kim, Seokhwan  and
      Hahm, Younggyun  and
      He, Zhong  and
      Lee, Tony Kyungil  and
      Santus, Enrico  and
      Bond, Francis  and
      Na, Seung-Hoon",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2022.coling-1.253/",
    pages = "2873--2882"
}