Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Impact

Output manipulation1

Attack surface / entry point

User input6Web pages and interfaces4Tool and skill descriptions0Retrieval corpus21Memory writes1

System component

MCP and skills4Memory7RAG1Guardrails and judges3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Impact：Output manipulationAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Memory writesSystem component：RAGClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2603.17239

    LAAF: A Systematic Red-Teaming Method and Automated Attack Framework for LPCI Vulnerabilities in Agentic LLM Systems

    提出 LAAF，分阶段自动攻击智能体系统的 LPCI 漏洞

    arXiv
    2603.17239
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gemini-2.0-flash-001, claude-3-haiku-20240307, meta-llama/llama-3.1-70b-instruct and others5
    AbstractLAAF does LPCI red teaming with taxonomy plus stage seeding.

    The authors state that LAAF is an automated red-teaming framework built specifically for LPCI in agentic LLMs. The issue to address is that encoded, delayed, and conditionally triggered payloads can persist in memory or RAG and re-enter across sessions, whereas Garak and PyRIT do not use the previous round's breakthrough results to seed the next stage across the six stages.

    Paper analysisRead analysis
You have reached the end