MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction Article Swipe

MAKE IMPACT

Xiaoling Hu , Eric Minwei Liu , Weizhou Wang , Xiangyu Guo , David Lie · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.04360

Retrieval-Augmented Generation (RAG) offers a solution to mitigate hallucinations in Large Language Models (LLMs) by grounding their outputs to knowledge retrieved from external sources. The use of private resources and data in constructing these external data stores can expose them to risks of extraction attacks, in which attackers attempt to steal data from these private databases. Existing RAG extraction attacks often rely on manually crafted prompts, which limit their effectiveness. In this paper, we introduce a framework called MARAGE for optimizing an adversarial string that, when appended to user queries submitted to a target RAG system, causes outputs containing the retrieved RAG data verbatim. MARAGE leverages a continuous optimization scheme that integrates gradients from multiple models with different architectures simultaneously to enhance the transferability of the optimized string to unseen models. Additionally, we propose a strategy that emphasizes the initial tokens in the target RAG data, further improving the attack's generalizability. Evaluations show that MARAGE consistently outperforms both manual and optimization-based baselines across multiple LLMs and RAG datasets, while maintaining robust transferability to previously unseen models. Moreover, we conduct probing tasks to shed light on the reasons why MARAGE is more effective compared to the baselines and to analyze the impact of our approach on the model's internal state.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2502.04360

PDF

https://arxiv.org/pdf/2502.04360

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4407308219

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4407308219

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2502.04360

Digital Object Identifier

Title

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-02-05

Full publication date if available

Authors

Xiaoling Hu, Eric Minwei Liu, Weizhou Wang, Xiangyu Guo, David Lie

List of authors in order

Landing page

https://arxiv.org/abs/2502.04360

Publisher landing page

PDF URL

https://arxiv.org/pdf/2502.04360

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2502.04360

Direct OA link when available

Concepts

Adversarial system, Computer science, Extraction (chemistry), Data mining, Information retrieval, Artificial intelligence, Chromatography, Chemistry

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload