Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913699230384128 |
|---|---|
| author | Zeng, Shenglai Zhang, Jiankun He, Pengfei Ren, Jie Zheng, Tianqi Lu, Hanqing Xu, Han Liu, Hui Xing, Yue Tang, Jiliang |
| author_facet | Zeng, Shenglai Zhang, Jiankun He, Pengfei Ren, Jie Zheng, Tianqi Lu, Hanqing Xu, Han Liu, Hui Xing, Yue Tang, Jiliang |
| contents | Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key contextual information from the original data. In the stage-2, we further enhance the privacy properties of the synthetic data through an agent-based iterative refinement process. Extensive experiments demonstrate that using our synthetic data as the retrieval context achieves comparable performance to using the original data while substantially reducing privacy risks. Our work takes the first step towards investigating the possibility of generating high-utility and privacy-preserving synthetic data for RAG, opening up new opportunities for the safe application of RAG systems in various domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14773 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data Zeng, Shenglai Zhang, Jiankun He, Pengfei Ren, Jie Zheng, Tianqi Lu, Hanqing Xu, Han Liu, Hui Xing, Yue Tang, Jiliang Cryptography and Security Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key contextual information from the original data. In the stage-2, we further enhance the privacy properties of the synthetic data through an agent-based iterative refinement process. Extensive experiments demonstrate that using our synthetic data as the retrieval context achieves comparable performance to using the original data while substantially reducing privacy risks. Our work takes the first step towards investigating the possibility of generating high-utility and privacy-preserving synthetic data for RAG, opening up new opportunities for the safe application of RAG systems in various domains. |
| title | Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2406.14773 |