MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915141667258368 |
|---|---|
| author | Hu, Xiao Liu, Eric Wang, Weizhou Guo, Xiangyu Lie, David |
| author_facet | Hu, Xiao Liu, Eric Wang, Weizhou Guo, Xiangyu Lie, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04360 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction Hu, Xiao Liu, Eric Wang, Weizhou Guo, Xiangyu Lie, David Computation and Language Cryptography and Security Machine Learning 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. |
| title | MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction |
| topic | Computation and Language Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2502.04360 |