收藏切换
Anti-Mapping Representation Perturbation for RAG Sensitive Information Protection
收藏切换
Xue Tan, Yi Zheng, Yunruo Zhang, Yiran Chen, Ping Chen*, Xiangyang Xue
Journal of Computer Research and Development | 2026, 63(11) : 2952 - 2962
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(11): 2952-2962
• Artificial Intelligence •
Anti-Mapping Representation Perturbation for RAG Sensitive Information Protection
Full
Xue Tan, Yi Zheng, Yunruo Zhang, Yiran Chen, Ping Chen*, Xiangyang Xue
Affiliations
  • Institute of Big Data, Fudan University, Shanghai 200433
  • born in 1997. PhD candidate. His main research interests include large language model security and privacy protection

    born in 1998. Master. His main research interests include computer vision and larger vision language models

    born in 1996. PhD, postdoc, professor. His main research interests include trusted AI and robustness certification

    born in 2002. Master candidate. Her main research interest includes large language model security

    born in 1985. PhD, professor. His main research interest includes AI security

    born in 1968. PhD, professor, PhD supervisor. His main research interests include computer vision, multimedia, and machine learning

About Author:

born in 1997. PhD candidate. His main research interests include large language model security and privacy protection

born in 1998. Master. His main research interests include computer vision and larger vision language models

born in 1996. PhD, postdoc, professor. His main research interests include trusted AI and robustness certification

born in 2002. Master candidate. Her main research interest includes large language model security

born in 1985. PhD, professor. His main research interest includes AI security

born in 1968. PhD, professor, PhD supervisor. His main research interests include computer vision, multimedia, and machine learning

Published: 2026-11-01 doi: 10.7544/issn1000-1239.202550713
Outline
收藏切换

Retrieval-augmented generation (RAG) systems extend the capability of large language models by incorporating external knowledge databases, enabling more accurate and up-to-date responses. However, this integration also introduces a novel privacy vulnerability: mapping attacks (MAs), which aim to infer whether a specific private fragment is indexed in the retrieval database and to uncover its retrieval behavior. Such attacks exploit both embedding-level signals and retrieval dynamics, posing a serious threat to sensitive data protection in RAG pipelines. Despite the growing awareness of privacy risks in RAG systems, there is currently no dedicated defense mechanism specifically designed to mitigate mapping attacks. We introduce AMRP-SIP, a dual-randomization framework that concurrently protects both embeddings of the documents and retrieval traces, while preserving state-of-the-art utility. AMRP-SIP comprises three lightweight stages. First, a random orthogonal projection compresses each query and document into a low-dimensional latent space, hiding raw embeddings and reducing downstream noise. Second, adaptive differential privacy injects cluster-adaptive Gaussian noise, ensuring (ε, δ) fragment-level privacy. Third, a score-dropout layer introduces randomness by perturbing similarity scores with noise and probabilistically dropping a portion of the retrieved documents with probability p, thereby obfuscating the retrieval trajectory. Experiments on Wiki-40B, PubMed-256, and IP-DataSet demonstrate that AMRP-SIP reduces the AUC of membership inference attack (MIA) from 0.75 to 0.27, while maintaining competitive performance in downstream RAG tasks.

retrieval-augmented generation (RAG)  /  mapping attack (MA)  /  differential privacy  /  membership inference attack (MIA)  /  random orthogonal projection
谭学, 郑毅, 张云若, 陈怡然, 陈平, 薛向阳. 面向检索增强生成敏感信息保护的抗测绘表征扰动. 计算机研究与发展, 2026 , 63 (11) : 2952 -2962 . DOI: 10.7544/issn1000-1239.202550713
Xue Tan, Yi Zheng, Yunruo Zhang, Yiran Chen, Ping Chen, Xiangyang Xue. Anti-Mapping Representation Perturbation for RAG Sensitive Information Protection[J]. Journal of Computer Research and Development, 2026 , 63 (11) : 2952 -2962 . DOI: 10.7544/issn1000-1239.202550713
Year 2026 volume 63 Issue 11
105
47
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550713
  • Receive Date:2025-09-30
  • Online Date:2026-11-17
  • Published:2026-11-01
Article Data
Affiliations
History
  • Received:2025-09-30
  • Revised:2026-06-09
  • Accepted:2026-06-22
Affiliations
    Institute of Big Data, Fudan University, Shanghai 200433
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550713
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT