RAGSieve

RAGSieve RAGSieve：在无可信参考的情况下检测 RAG 中的知识投毒文档 的代码。 RAGSieve 在检索增强生成（RAG）系统的两个环节检测知识投毒文档。RSQ 是一种在线过滤器：它将为生成而选出的五篇文档与当前查询的第 6--20 名进行评分对比。RSG 是一种离线扫描器：它将语料库中的每篇文档与其自身的语义--词汇邻域进行评分对比。该软件包包含论文中使用的 RSQ 和 RSG 实现、精确的全语料库检索、Top-5 过滤与补充、文档级评估，以及一个紧凑的可运行示例。 仓库内容 data/datasets/ NQ、HotpotQA 和 MS MARCO 文本知识库...

TrustworthyRAG

Trustworthy RAG（可信赖的 RAG） 一个用于检测检索增强生成（RAG）系统中错误信息与知识投毒的评估代理。 概述 本项目实现了一个 Trustworthy RAG 框架 ，其中集成有评估代理（Evaluation Agent） ，通过三个互补的分析组件评估 RAG 响应的可靠性： NLI 验证器（NLI Verifier） - 通过自然语言推断（BART-MNLI）进行事实一致性检查 投毒检测器（Poison Detector） - 多信号对抗性内容检测（语言学、结构、语义、文档内/跨文档 NLI） 信任指数计算器（Trust Index Calculator） -...

CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

Retrieval-Augmented Code Generation RACG improves LLM-based software development by retrieving external code artifacts, documentation, and patches, and incorporating them into the generation context. This reliance on external knowledge introduces a critical trust boundary: poisoned artifacts can...

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

Retrieval-Augmented Generation RAG grounds Large Language Model LLM outputs in external knowledge, but RAG systems usually trust whatever they retrieve, creating a Security-Reliability Gap: high semantic relevance does not guarantee factual truth. Adversaries exploit this through knowledge...

Defending Retrieval-Augmented Intrusion Detection against Knowledge Poisoning and Prompt Injection

Retrieval-Augmented Generation RAG enables large language models to classify network flows and generate human-readable incident reports by retrieving semantically similar historical traffic from a vector knowledge base. However, the retrieval layer introduces vulnerabilities to knowledge poisonin...

PURPOSE: Poisoning Conflict Resolution in RAG Via Proxy-Fact-Grounded Updates

In Retrieval-Augmented Generation RAG, post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target...

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

Large Language Models LLMs enhanced with Retrieval-Augmented Generation RAG have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly...