on-premise rag deployment

This work addresses the challenge enterprises face in adopting cloud-based Retrieval-Augmented Generation (RAG) systems due to stringent data compliance requirements, compounded by the absence of a standardized reference architecture for on-premises deployment. To bridge this gap, we propose the first enterprise-grade, on-premises RAG engineering framework grounded in the 4+1 architectural view model. Our solution encompasses an end-to-end reference architecture, a deployable open-source reference application, a localized toolchain, and a customized CI/CD pipeline. This comprehensive framework fills a critical void in the standardized implementation of enterprise-scale, on-premises RAG systems. The complete blueprint and source code have been open-sourced on GitHub, and preliminary validation through industry partnerships and expert interviews demonstrates its practical utility and feasibility.

Existing centralized RAG systems suffer from high operational costs, privacy vulnerabilities, and—upon decentralization—heterogeneous data source reliability. To address these challenges, this paper proposes the first blockchain-based decentralized RAG framework. Our method integrates (1) a dynamic reliability scoring mechanism that assesses and weights multi-source retrieval in real time based on contribution quality; (2) smart contracts for transparent, tamper-proof, and decentralized management of score generation, updates, and verification; and (3) a hybrid architecture combining decentralized storage, batched state synchronization, and multi-source fusion retrieval using Llama-3B/8B models. Experiments under low-reliability simulated conditions demonstrate a 10.7% improvement in retrieval accuracy and generation quality, performance approaching that of centralized baselines, and a 56% reduction in marginal cost. The system is open-sourced.

Integrating sensitive data into Retrieval-Augmented Generation (RAG) systems introduces novel security and privacy risks across the end-to-end pipeline—spanning data preprocessing, storage, retrieval, and large language model (LLM) generation. Method: We systematically identify and characterize the full RAG attack surface, proposing the first RAG-specific attack surface definition methodology. Our structured governance framework integrates domain-specific RAG properties with established standards—including ISO/IEC 27001 and NIST SP 800-53—enabling bidirectional mapping between security controls and compliance requirements. We conduct rigorous risk modeling, attack tree analysis, and RAG pipeline security auditing. Contribution/Results: The work yields a practical, actionable security checklist, a mitigation strategy matrix, and an implementation guide. It directly supports enterprise RAG deployments in achieving compliance with China’s Multi-Level Protection Scheme (MLPS) Level 3 and the GDPR—thereby bridging critical theoretical and practical gaps in RAG security governance.

To address the security risk of private knowledge base leakage in Retrieval-Augmented Generation (RAG) systems, this paper proposes the first end-to-end scheme supporting joint searchable encryption for both raw text and semantic embeddings. Methodologically, it integrates homomorphic searchable symmetric encryption (HSSE) with secure embedding mapping to enable full-cycle operations—retrieval, re-ranking, and generation—entirely over ciphertexts, while maintaining compatibility with mainstream LLMs and retrieval backends (e.g., FAISS, Chroma). Theoretically, we provide formal security proofs and identify fundamental flaws in existing approaches concerning robustness and model dependency. Experimentally, our scheme preserves 98.3% of original accuracy across multiple benchmarks, resists white-box and membership inference attacks, ensures zero plaintext recovery under key compromise, and passes preliminary ISO/IEC 27001 compliance verification.

RAG systems face critical security threats—including data leakage and poisoning—yet existing defenses lack formal security guarantees, suffer from poor interpretability, and are vulnerable to adaptive attacks. To address this, we propose SAG, the first provably secure RAG framework. SAG employs end-to-end encryption prior to storage, simultaneously safeguarding both raw documents and their vector embeddings. We introduce the first cryptographically grounded formal security model for RAG, rigorously proving confidentiality and integrity under standard assumptions. By integrating ciphertext-based retrieval with protected embedding representations, SAG effectively mitigates state-of-the-art attacks across multiple benchmarks. Experiments demonstrate that SAG maintains competitive retrieval accuracy and generation quality while substantially enhancing security—achieving up to 98% attack mitigation without compromising latency or utility. Our work establishes both theoretical foundations and practical mechanisms for verifiably secure RAG deployment.

研究通过比较不同数据库结构的RAG配置，解决REST API误用自动修复问题，发现按版本和内容类型组织规范能有效提高修复率。

This study addresses the structured attack surfaces and risk assessment challenges introduced by multi-stage pipelines in Retrieval-Augmented Generation (RAG) systems. To this end, it proposes a security metamodel framework that integrates explicit causal correlations. Through iterative structured literature analysis and knowledge graph modeling, the metamodel is instantiated into a navigable threat catalog, enabling deployment configuration-based risk profiling and interactive visualization. This work bridges critical gaps in RAG offense-defense asymmetry and output integrity coverage. Furthermore, its applicability is validated across text, graph, and multimodal configurations, demonstrating significant improvements in risk identification efficiency for security engineers.

This work addresses data staleness, tenant leakage, and combinatorial query explosion in production-grade retrieval-augmented generation (RAG) systems caused by decoupled data layers. To resolve these issues, the authors propose a unified data layer architecture built on PostgreSQL that, for the first time, integrates vector retrieval and structured filtering within a single database. By leveraging pgvector with HNSW indexing and a hybrid hierarchical design, the system eliminates cross-system synchronization overhead while guaranteeing strict tenant isolation and strong data consistency. Experimental results on a dataset of 50,000 documents demonstrate a 92% reduction in latency for date-filtered queries and a 74% reduction for tenant-scoped queries, alongside a 93% decrease in synchronization code, achieving zero data inconsistency and enabling efficient, secure RAG.

This work addresses critical security risks in enterprise retrieval-augmented generation (RAG) and agent systems under multi-tenancy, where cross-tenant data leakage and unsafe tool invocations arise due to relevance-based ranking that disregards access control. To resolve this, the authors propose a hierarchical isolation architecture that deeply integrates attribute-based access control (ABAC) into the entire RAG and agent pipeline. By introducing policy-aware data ingestion, retrieval-time gating mechanisms, and server-side multi-turn agent orchestration, all security-critical operations are centralized on the server. This design ensures strict tenant isolation and regulatory compliance while preserving client-side flexibility and low-latency responsiveness. Experiments based on the OGX framework demonstrate that the proposed approach completely eliminates cross-tenant data leakage with negligible performance overhead.

This work addresses the security and privacy risks inherent in Retrieval-Augmented Generation (RAG) systems—such as sensitive data leakage and knowledge base tampering—by proposing the first unified threat taxonomy that spans the entire RAG pipeline, including retrieval, context construction, and generation. It systematically analyzes attack surfaces across centralized, on-device (Micro-RAG), federated, and hybrid deployment paradigms, and integrates corresponding defense mechanisms leveraging techniques like differential privacy, secure aggregation, and encrypted retrieval. The study provides a comprehensive survey of existing research, clarifies the trade-offs between privacy and utility, highlights practical deployment challenges, and identifies critical open problems, thereby establishing a theoretical foundation and charting future directions for developing trustworthy, secure, and robust RAG systems.