首个可证明安全的RAG框架，防止数据泄露与投毒攻击
Provably Secure Retrieval-Augmented Generation
- 采用全加密存储，保护检索内容与向量嵌入
- 在多个基准数据集上抵御主流攻击，验证安全性
- 提供形式化安全证明，适合高安全需求场景
尽管检索增强生成（RAG）系统已广泛应用，但其面临的数据泄露和数据投毒等隐私与安全风险尚未得到系统性解决。现有防御策略主要依赖启发式过滤或增强检索器鲁棒性，存在可解释性差、缺乏形式化安全保证、易受自适应攻击等问题。本文提出首个可证明安全的RAG框架（SAG）。该框架采用预存储全加密方案，双重保护检索内容与向量嵌入，确保仅授权实体可访问数据。通过形式化安全证明，严格验证了该方案在计算安全模型下的机密性与完整性。在多个基准数据集上的大量实验表明，该框架能有效抵御多种前沿攻击。本工作为可验证安全的RAG系统建立了理论基础与实践范式，推动基于AI的服务迈向形式化安全保障。
原文摘要 · Abstract (English)
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been systematically addressed yet. Existing defense strategies primarily rely on heuristic filtering or enhancing retriever robustness, which suffer from limited interpretability, lack of formal security guarantees, and vulnerability to adaptive attacks. To address these challenges, this paper proposes the first provably secure framework for RAG systems(SAG). Our framework employs a pre-storage full-encryption scheme to ensure dual protection of both retrieved content and vector embeddings, guaranteeing that only authorized entities can access the data. Through formal security proofs, we rigorously verify the scheme's confidentiality and integrity under a computational security model. Extensive experiments across multiple benchmark datasets demonstrate that our framework effectively resists a range of state-of-the-art attacks. This work establishes a theoretical foundation and practical paradigm for verifiably secure RAG systems, advancing AI-powered services toward formally guaranteed security.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。