Abstract
Text-based adversarial attacks are becoming more commonplace and accessible to general internet users. As these attacks proliferate, the need to address the gap in model robustness becomes imminent. While retraining on adversarial data may increase performance, there remains an additional class of character-level attacks on which these models falter. Additionally, the process to retrain a model is time and resource intensive, creating a need for a lightweight, reusable defense. In this work, we propose the Adversarial Text Normalizer, a novel method that restores baseline performance on attacked content with low computational overhead. We evaluate the efficacy of the normalizer on two problem areas prone to adversarial attacks, i.e. Hate Speech and Natural Language Inference. We find that text normalization provides a task-agnostic defense against character-level attacks that can be implemented supplementary to adversarial retraining solutions, which are more suited for semantic alterations.- Anthology ID:
- 2022.naacl-industry.30
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
- Month:
- July
- Year:
- 2022
- Address:
- Hybrid: Seattle, Washington + Online
- Editors:
- Anastassia Loukina, Rashmi Gangadharaiah, Bonan Min
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 268–279
- Language:
- URL:
- https://aclanthology.org/2022.naacl-industry.30
- DOI:
- 10.18653/v1/2022.naacl-industry.30
- Cite (ACL):
- Joanna Bitton, Maya Pavlova, and Ivan Evtimov. 2022. Adversarial Text Normalization. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 268–279, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
- Cite (Informal):
- Adversarial Text Normalization (Bitton et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.naacl-industry.30.pdf
- Data
- ANLI