Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Attacker access

Black-box6Gray-box1

Layer

Application layer1Training and data layer0

System component

RAG1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attacker access：Gray-boxLayer：Application layerLayer：Training and data layerSystem component：RAGClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.14649

    CIG-MIA：利用上下文信息增益对 RAG 系统发起成员推断攻击

    提出 CIG-MIA，用上下文信息增益推断 RAG 知识库成员身份

    arXiv
    2609.14649
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Gray-box, Black-box
    Evaluated models
    Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-2-13b-chat-hf and others6
    AbstractCIG-MIA 用注入前后的答案似然差推断 RAG 库成员，灰盒可分性高于所列基线。

    CIG-MIA 是针对 RAG 外部知识库的成员推断攻击，同时覆盖灰盒和纯文本黑盒。

    Paper analysisRead analysis
You have reached the end