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
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.
| 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 |