Typos that Broke the RAG’s Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, Jong Park


Abstract
The robustness of recent Large Language Models (LLMs) has become increasingly crucial as their applicability expands across various domains and real-world applications. Retrieval-Augmented Generation (RAG) is a promising solution for addressing the limitations of LLMs, yet existing studies on the robustness of RAG often overlook the interconnected relationships between RAG components or the potential threats prevalent in real-world databases, such as minor textual errors. In this work, we investigate two underexplored aspects when assessing the robustness of RAG: 1) vulnerability to noisy documents through low-level perturbations and 2) a holistic evaluation of RAG robustness. Furthermore, we introduce a novel attack method, the Genetic Attack on RAG (GARAG), which targets these aspects. Specifically, GARAG is designed to reveal vulnerabilities within each component and test the overall system functionality against noisy documents. We validate RAG robustness by applying our GARAG to standard QA datasets, incorporating diverse retrievers and LLMs. The experimental results show that GARAG consistently achieves high attack success rates. Also, it significantly devastates the performance of each component and their synergy, highlighting the substantial risk that minor textual inaccuracies pose in disrupting RAG systems in the real world. Code is available at https://github.com/zomss/GARAG.
Anthology ID:
2024.findings-emnlp.161
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2826–2844
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.161
DOI:
Bibkey:
Cite (ACL):
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, and Jong Park. 2024. Typos that Broke the RAG’s Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2826–2844, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Typos that Broke the RAG’s Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations (Cho et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.161.pdf
Software:
 2024.findings-emnlp.161.software.zip