Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Impact

Data and privacy leaks11Output manipulation27Availability and reliability2

Layer

Application layer2Training and data layer0

System component

MCP and skills6Memory3RAG2Guardrails and judges4Vision3Multimodal5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityLayer：Application layerLayer：Training and data layerSystem component：RAGClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.04691

    RAGStress：评测知识库退化下 RAG 鲁棒性的受控基准

    提出 RAGStress 受控基准，评测知识库退化下的 RAG

    arXiv
    2610.04691
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Claude Sonnet 4, Claude Opus 4.6, DeepSeek R1 and others5
    Abstract作者用 RAGStress 比较五系统。

    RAGStress 是知识库损坏下的 RAG 受控压力测试。作者明确不把它当作模型排行榜。

    Paper analysisRead analysis
  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