White-Box Multi-Objective Adversarial Attack on Dialogue Generation

Yufei Li, Zexin Li, Yingfan Gao, Cong Liu


Abstract
Pre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which inspires our curiosity about their robustness in DG systems. One main challenge of attacking DG models is that perturbations on the current sentence can hardly degrade the response accuracy because the unchanged chat histories are also considered for decision-making. Instead of merely pursuing pitfalls of performance metrics such as BLEU, ROUGE, we observe that crafting adversarial samples to force longer generation outputs benefits attack effectiveness—the generated responses are typically irrelevant, lengthy, and repetitive. To this end, we propose a white-box multi-objective attack method called DGSlow. Specifically, DGSlow balances two objectives—generation accuracy and length, via a gradient-based multi-objective optimizer and applies an adaptive searching mechanism to iteratively craft adversarial samples with only a few modifications. Comprehensive experiments on four benchmark datasets demonstrate that DGSlow could significantly degrade state-of-the-art DG models with a higher success rate than traditional accuracy-based methods. Besides, our crafted sentences also exhibit strong transferability in attacking other models.
Anthology ID:
2023.acl-long.100
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1778–1792
Language:
URL:
https://aclanthology.org/2023.acl-long.100
DOI:
10.18653/v1/2023.acl-long.100
Bibkey:
Cite (ACL):
Yufei Li, Zexin Li, Yingfan Gao, and Cong Liu. 2023. White-Box Multi-Objective Adversarial Attack on Dialogue Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1778–1792, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
White-Box Multi-Objective Adversarial Attack on Dialogue Generation (Li et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.100.pdf
Video:
 https://aclanthology.org/2023.acl-long.100.mp4