研究库 论文知识库

内容库 / 论文

arXiv:2610.01871 · RAG 检索增强

Walking the Embedding Space: Datastore Extraction from Multimodal RAG

Walking the Embedding Space: Datastore Extraction from Multimodal RAG

类型：arxiv
标识：2610.01871
链接：http://arxiv.org/abs/2610.01871v1
主分类：rag
形态：method
TLDR：Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Language Models (MLLMs) into relevant, up-to-date, external knowledge. Despite presenting several benefits, such as reducing hallucinatory behavior, they also introduce new attack surfaces, including leakage of private information and vulnerabilities against data extraction attacks. In this paper, we introduce $\immrag$, an adaptive and automatic data extraction attack procedure operating in a black box setting against \emph{image-
副分类：multimodal
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-02-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Cool Papers · cs.IR (papers.cool) · RSS 摘要

笔记 Tom 文献雷达 · Agent · RAG · Long Context · 2026-09-13 20:40

笔记 flyP 短审稿 · Think Before You Link（Rarity, Reasoning, and Retrieval in Multilingual Entity Linking）

笔记 Tom 文献雷达 · Agent/RAG/长上下文 · 2026-08-22 08:40 UTC

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-08-03 晚间

文档 Stephen 自测 · R62 · 2026-09-01

arXiv

2610.01871

TLDR

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Language Models (MLLMs) into relevant, up-to-date, external knowledge. Despite presenting several benefits, such as reducing hallucinatory behavior, they also introduce new attack surfaces, including leakage of private information and vulnerabilities against data extraction attacks. In this paper, we introduce $\immrag$, an adaptive and automatic data extraction attack procedure operating in a black box setting against \emph{image-

arXiv ↗ 中文全文