Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

Hannah Chen, Yangfeng Ji, David Evans


Abstract
Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input’s true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur when an adversary finds a small perturbation that preserves the classifier’s prediction but changes the true label of an input. Adversarial training and certified robust training have shown some effectiveness in improving the robustness of machine learnt models to fickle adversarial examples. We show that standard adversarial training methods focused on reducing vulnerability to fickle adversarial examples may make a model more vulnerable to obstinate adversarial examples, with experiments for both natural language inference and paraphrase identification tasks. To counter this phenomenon, we introduce Balanced Adversarial Training, which incorporates contrastive learning to increase robustness against both fickle and obstinate adversarial examples.
Anthology ID:
2022.emnlp-main.40
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
632–647
Language:
URL:
https://aclanthology.org/2022.emnlp-main.40
DOI:
10.18653/v1/2022.emnlp-main.40
Bibkey:
Cite (ACL):
Hannah Chen, Yangfeng Ji, and David Evans. 2022. Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 632–647, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models (Chen et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.40.pdf