---
id: 20260731-T0-10
title: "RAGuard：针对RAG系统数据投毒攻击的多层防御框架"
title_en: "RAGuard: A Layered Defense Against Data Poisoning in RAG Systems"
url: https://ai.daily.yangsir.net/daily/20260731-T0-10
issue_date: 2026-07-31
publish_date: 2026-07-30T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2607.26339
---

# RAGuard：针对RAG系统数据投毒攻击的多层防御框架

arXiv新论文提出RAGuard，一个针对检索增强生成（RAG）系统的分层防御框架。RAG系统依赖外部语料库检索来增强大模型回答，但这种方法容易被恶意注入的文本片段操纵。RAGuard通过在检索、过滤和生成三个阶段分别部署检测与清洗机制，有效抵御语料库投毒攻击。该框架为敏感领域（如金融、医疗）部署RAG应用提供了更安全的基线方案。

## English Version

**RAGuard: A Layered Defense Against Data Poisoning in RAG Systems**

A new paper on arXiv introduces RAGuard, a layered defense framework for Retrieval-Augmented Generation (RAG) systems against corpus poisoning. RAG systems ground LLMs in external data, making them vulnerable to maliciously injected passages. RAGuard deploys detection and sanitization mechanisms across retrieval, filtering, and generation stages. It provides a safer baseline for deploying RAG applications in sensitive fields like finance and healthcare.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2607.26339)

**详情页**：https://ai.daily.yangsir.net/daily/20260731-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*