RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems

Yasaman Boreshban, Seyed Morteza Mirbostani, Seyedeh Fatemeh Ahmadi, Gita Shojaee, Fatemeh Kamani, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel


Abstract
Question answering (QA) systems have reached human-level accuracy; however, these systems are not robust enough and are vulnerable to adversarial examples. Recently, adversarial attacks have been widely investigated in text classification. However, there have been few research efforts on this topic in QA. In this article, we have modified the attack algorithms widely used in text classification to fit those algorithms for QA systems. We have evaluated the impact of various attack methods on QA systems at character, word, and sentence levels. Furthermore, we have developed a new framework, named RobustQA, as the first open-source toolkit for investigating textual adversarial attacks in QA systems. RobustQA consists of seven modules: Tokenizer, Victim Model, Goals, Metrics, Attacker, Attack Selector, and Evaluator. It currently supports six different attack algorithms. Furthermore, the framework simplifies the development of new attack algorithms in QA. The source code and documentation of RobustQA are available at https://github.com/mirbostani/RobustQA.
Anthology ID:
2023.emnlp-demo.24
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
December
Year:
2023
Address:
Singapore
Editors:
Yansong Feng, Els Lefever
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
274–285
Language:
URL:
https://aclanthology.org/2023.emnlp-demo.24
DOI:
10.18653/v1/2023.emnlp-demo.24
Bibkey:
Cite (ACL):
Yasaman Boreshban, Seyed Morteza Mirbostani, Seyedeh Fatemeh Ahmadi, Gita Shojaee, Fatemeh Kamani, Gholamreza Ghassem-Sani, and Seyed Abolghasem Mirroshandel. 2023. RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 274–285, Singapore. Association for Computational Linguistics.
Cite (Informal):
RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems (Boreshban et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-demo.24.pdf
Video:
 https://aclanthology.org/2023.emnlp-demo.24.mp4