ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914578943705088 |
|---|---|
| author | Lyu, Xingyu He, Jianfeng Wang, Ning Hu, Yidan Li, Tao Chen, Danjue Li, Shixiong Chen, Yimin |
| author_facet | Lyu, Xingyu He, Jianfeng Wang, Ning Hu, Yidan Li, Tao Chen, Danjue Li, Shixiong Chen, Yimin |
| contents | Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data extraction attacks, where adversaries can extract private data by embedding malicious commands into user queries. Despite their feasibility, existing attacks typically suffer from low data extraction rates and limited practical effectiveness. Here, we propose ALDEN, a novel attack that effectively and efficiently extracts private data from RAGs. First, we employ active learning to diversify malicious queries and improve data extraction rates. Second, we observe that the data distribution of the underlying knowledge base provides valuable guidance for query generation and introduce a decay-based dynamic algorithm to estimate the corresponding topic distribution. By combining them together, we demonstrate that ALDEN substantially outperforms state-of-the-art methods through comprehensive evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18762 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation Lyu, Xingyu He, Jianfeng Wang, Ning Hu, Yidan Li, Tao Chen, Danjue Li, Shixiong Chen, Yimin Information Retrieval Artificial Intelligence Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data extraction attacks, where adversaries can extract private data by embedding malicious commands into user queries. Despite their feasibility, existing attacks typically suffer from low data extraction rates and limited practical effectiveness. Here, we propose ALDEN, a novel attack that effectively and efficiently extracts private data from RAGs. First, we employ active learning to diversify malicious queries and improve data extraction rates. Second, we observe that the data distribution of the underlying knowledge base provides valuable guidance for query generation and introduce a decay-based dynamic algorithm to estimate the corresponding topic distribution. By combining them together, we demonstrate that ALDEN substantially outperforms state-of-the-art methods through comprehensive evaluations. |
| title | ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2605.18762 |