Adversarial Attack on Sentiment Classification

Yi-Ting Tsai, Min-Chu Yang, Han-Yu Chen


Abstract
In this paper, we propose a white-box attack algorithm called “Global Search” method and compare it with a simple misspelling noise and a more sophisticated and common white-box attack approach called “Greedy Search”. The attack methods are evaluated on the Convolutional Neural Network (CNN) sentiment classifier trained on the IMDB movie review dataset. The attack success rate is used to evaluate the effectiveness of the attack methods and the perplexity of the sentences is used to measure the degree of distortion of the generated adversarial examples. The experiment results show that the proposed “Global Search” method generates more powerful adversarial examples with less distortion or less modification to the source text.
Anthology ID:
W19-4824
Volume:
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
233–240
Language:
URL:
https://aclanthology.org/W19-4824
DOI:
10.18653/v1/W19-4824
Bibkey:
Cite (ACL):
Yi-Ting Tsai, Min-Chu Yang, and Han-Yu Chen. 2019. Adversarial Attack on Sentiment Classification. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 233–240, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Adversarial Attack on Sentiment Classification (Tsai et al., BlackboxNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4824.pdf
Data
IMDb Movie Reviews