Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification

Yichao Zhou, Jyun-Yu Jiang, Kai-Wei Chang, Wei Wang

Abstract
Adversarial attacks against machine learning models have threatened various real-world applications such as spam filtering and sentiment analysis. In this paper, we propose a novel framework, learning to discriminate perturbations (DISP), to identify and adjust malicious perturbations, thereby blocking adversarial attacks for text classification models. To identify adversarial attacks, a perturbation discriminator validates how likely a token in the text is perturbed and provides a set of potential perturbations. For each potential perturbation, an embedding estimator learns to restore the embedding of the original word based on the context and a replacement token is chosen based on approximate kNN search. DISP can block adversarial attacks for any NLP model without modifying the model structure or training procedure. Extensive experiments on two benchmark datasets demonstrate that DISP significantly outperforms baseline methods in blocking adversarial attacks for text classification. In addition, in-depth analysis shows the robustness of DISP across different situations.
Anthology ID:
D19-1496
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4904–4913
Language:
URL:
https://aclanthology.org/D19-1496
DOI:
10.18653/v1/D19-1496
Bibkey:
Cite (ACL):
Yichao Zhou, Jyun-Yu Jiang, Kai-Wei Chang, and Wei Wang. 2019. Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4904–4913, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification (Zhou et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/D19-1496.pdf
Code
 joey1993/bert-defender
Data
CoLA, IMDb Movie Reviews, SST, SST-2
PDF Search Code