研究库 论文知识库

内容库 / 论文

arXiv:2609.16818 · RAG 检索增强

InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation

InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation

类型：arxiv
标识：2609.16818
链接：http://arxiv.org/abs/2609.16818v1
主分类：rag
形态：method
TLDR：Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but have been demonstrated to be vulnerable to corpus poisoning. Existing poisoning attacks against RAG largely focus on single-point explicit injection, where the malicious payload is fully encapsulated within a single document. Consequently, recent mitigation mechanisms have evolved to identify and diminish these threats effectively. In this paper, we first verify that existing mitigation mechanisms are insufficient for a new class of threats: indirect logic induction. Motivated by this
副分类：risk
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 chrismmt/mcp-adversarial-suite

笔记 Tom 文献雷达 · Agent / RAG / 长上下文 · 2026-08-22

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-07-07 14:30

仓库 Jacquelinepersha/ai-cybersecurity-masterclass

笔记 Tom 文献雷达 · Agent + RAG + Long-Context · 2026-08-19

笔记 Tom 文献雷达 · Agent · RAG · 长上下文

arXiv

2609.16818

TLDR

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but have been demonstrated to be vulnerable to corpus poisoning. Existing poisoning attacks against RAG largely focus on single-point explicit injection, where the malicious payload is fully encapsulated within a single document. Consequently, recent mitigation mechanisms have evolved to identify and diminish these threats effectively. In this paper, we first verify that existing mitigation mechanisms are insufficient for a new class of threats: indirect logic induction. Motivated by this

arXiv ↗ 中文全文