Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval

Computer Science > Cryptography and Security [Submitted on 10 Apr 2026] Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval Yu Liu, Kun Peng, Wenxiao Zhang, Fangfang Yuan, Cong Cao, Wenxuan Lu, Yanbing Liu 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. Comments: Accepted by DASFAA 2026 Subjects: Cryptography and Security (cs.CR); Information Retrieval (cs.IR) Cite as: arXiv:2604.09541 [cs.CR]   (or arXiv:2604.09541v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.09541 Focus to learn more Submission history From: Yu Liu [view email] [v1] Fri, 10 Apr 2026 17:58:06 UTC (8,587 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)