Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack technique

Gradient and representation optimization6Automated search10Encoding and obfuscation6Role-play and persuasion6Conversation structure manipulation3Cross-modal payloads4Dormant triggers2

System type

LLM applications2AI Agent30coding agent7Multi-agent systems3

Layer

Application layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack technique：Dormant triggersSystem type：LLM applicationsLayer：Application layerClear all

Another 261papers 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
  2. AttacksarXiv 2512.01335

    EmoRAG 研究揭示 RAG 检索对表情符号扰动的脆弱性

    提出 EmoRAG，向查询与知识库注入同一表情以劫持 RAG 检索

    arXiv
    2512.01335
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    SPECTER, Contriever, Qwen2-7B and others11
    AbstractEmoRAG 用表情联动查询与库文本。

    EmoRAG 测量 RAG 对符号扰动的反应：同一表情同时出现在查询和库文本里时，检索会偏离语义匹配。作者要检查的是，检索是否真由语义相关性决定。

    Paper analysisRead analysis
You have reached the end