Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter5

Impact

Unauthorized actions45Data and privacy leaks12Output manipulation50Availability and reliability2

Attack surface / entry point

User input3Web pages and interfaces3Documents and messages1Tool and skill descriptions3Retrieval corpus1Training data0Distribution channels3

Layer

Application layer2Training and data layer6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityAttack surface / entry point：Documents and messagesAttack surface / entry point：Retrieval corpusAttack surface / entry point：Training dataLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2603.03919

    When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking Attacks in RAG

    提出 TabooRAG，用单篇文档迁移阻断 RAG 对良性查询的回答

    arXiv
    2603.03919
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama-3-8B-Instruct, Ministral-3-8B-Instruct-2512, Gemma-3-12B-it and others9
    AbstractTabooRAG 用代理侧风险文档迁移阻断 RAG。

    TabooRAG 是面向 RAG 可用性的可迁移阻断攻击，不改已有文档，也不读取目标反馈。

    Paper analysisRead analysis
You have reached the end