Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Attack surface / entry point

User input15Web pages and interfaces4Documents and messages3Tool and skill descriptions0Code repositories and dependencies1Retrieval corpus26

Layer

Application layer1

System component

MCP and skills53Memory7RAG1Guardrails and judges14Monitors8Permissions and sandboxing21
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.
Attack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Code repositories and dependenciesLayer：Application layerSystem component：RAGClear all

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

  1. AttacksarXiv 2609.02774

    CodePoisonRAG：针对检索增强代码生成的知识投毒攻击

    提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞

    arXiv
    2609.02774
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B

    AbstractCodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。

    Paper analysisRead analysis
You have reached the end