Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense

Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee


Abstract
We proposes a novel algorithm, ANTHRO, that inductively extracts over 600K human-written text perturbations in the wild and leverages them for realistic adversarial attack. Unlike existing character-based attacks which often deductively hypothesize a set of manipulation strategies, our work is grounded on actual observations from real-world texts. We find that adversarial texts generated by ANTHRO achieve the best trade-off between (1) attack success rate, (2) semantic preservation of the original text, and (3) stealthiness–i.e. indistinguishable from human writings hence harder to be flagged as suspicious. Specifically, our attacks accomplished around 83% and 91% attack success rates on BERT and RoBERTa, respectively. Moreover, it outperformed the TextBugger baseline with an increase of 50% and 40% in terms of semantic preservation and stealthiness when evaluated by both layperson and professional human workers. ANTHRO can further enhance a BERT classifier’s performance in understanding different variations of human-written toxic texts via adversarial training when compared to the Perspective API.
Anthology ID:
2022.findings-acl.232
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2953–2965
Language:
URL:
https://aclanthology.org/2022.findings-acl.232
DOI:
10.18653/v1/2022.findings-acl.232
Bibkey:
Cite (ACL):
Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, and Dongwon Lee. 2022. Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2953–2965, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense (Le et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.232.pdf
Video:
 https://aclanthology.org/2022.findings-acl.232.mp4
Code
 lethaiq/perturbations-in-the-wild