Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo


Abstract
Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative search engines may not always be accurate. Nonetheless, retrieval-augmented generation exacerbates safety concerns, since adversaries may successfully evade the entire system by subtly manipulating the most vulnerable part of a claim. To this end, we propose evaluating the robustness of generative search engines in the realistic and high-risk setting, where adversaries have only black-box system access and seek to deceive the model into returning incorrect responses. Through a comprehensive human evaluation of various generative search engines, such as Bing Chat, PerplexityAI, and YouChat across diverse queries, we demonstrate the effectiveness of adversarial factual questions in inducing incorrect responses. Moreover, retrieval-augmented generation exhibits a higher susceptibility to factual errors compared to LLMs without retrieval. These findings highlight the potential security risks of these systems and emphasize the need for rigorous evaluation before deployment. The dataset and code will be publicly available.
Anthology ID:
2024.findings-acl.633
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10650–10671
Language:
URL:
https://aclanthology.org/2024.findings-acl.633
DOI:
10.18653/v1/2024.findings-acl.633
Bibkey:
Cite (ACL):
Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, and Zhijiang Guo. 2024. Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10650–10671, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (Hu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.633.pdf