Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915930414514176 |
|---|---|
| author | Liu, Yu Peng, Kun Zhang, Wenxiao Yuan, Fangfang Cao, Cong Lu, Wenxuan Liu, Yanbing |
| author_facet | Liu, Yu Peng, Kun Zhang, Wenxiao Yuan, Fangfang Cao, Cong Lu, Wenxuan Liu, Yanbing |
| contents | Retrieval Augmented Generation (RAG) systems deployed across organizational boundaries face fundamental tensions between security, accuracy, and efficiency. Current encryption methods expose plaintext during decryption, while federated architectures prevent resource integration and incur substantial overhead. We introduce Trans-RAG, implementing a novel vector space language paradigm where each organization's knowledge exists in a mathematically isolated semantic space. At the core lies vector2Trans, a multi-stage transformation technique that enables queries to dynamically "speak" each organization's vector space "language" through query-centric transformations, eliminating decryption overhead while maintaining native retrieval efficiency. Security evaluations demonstrate near-orthogonal vector spaces with 89.90° angular separation and 99.81% isolation rates. Experiments across 8 retrievers, 3 datasets, and 3 LLMs show minimal accuracy degradation (3.5% decrease in nDCG@10) and significant efficiency improvements over homomorphic encryption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09541 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval Liu, Yu Peng, Kun Zhang, Wenxiao Yuan, Fangfang Cao, Cong Lu, Wenxuan Liu, Yanbing Cryptography and Security Information Retrieval Retrieval Augmented Generation (RAG) systems deployed across organizational boundaries face fundamental tensions between security, accuracy, and efficiency. Current encryption methods expose plaintext during decryption, while federated architectures prevent resource integration and incur substantial overhead. We introduce Trans-RAG, implementing a novel vector space language paradigm where each organization's knowledge exists in a mathematically isolated semantic space. At the core lies vector2Trans, a multi-stage transformation technique that enables queries to dynamically "speak" each organization's vector space "language" through query-centric transformations, eliminating decryption overhead while maintaining native retrieval efficiency. Security evaluations demonstrate near-orthogonal vector spaces with 89.90° angular separation and 99.81% isolation rates. Experiments across 8 retrievers, 3 datasets, and 3 LLMs show minimal accuracy degradation (3.5% decrease in nDCG@10) and significant efficiency improvements over homomorphic encryption. |
| title | Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval |
| topic | Cryptography and Security Information Retrieval |
| url | https://arxiv.org/abs/2604.09541 |