Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack type

Prompt injection4Poisoning and backdoors1

Attack technique

Encoding and obfuscation1Dormant triggers6

Attack surface / entry point

Tool responses1Tool and skill descriptions3Retrieval corpus3Memory writes3Distribution channels4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsAttack technique：Encoding and obfuscationAttack surface / entry point：Tool responsesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2507.10457

    论文提出 LPCI：针对 Agent 逻辑层与持久记忆的提示控制注入攻击

    提出 LPCI，把延迟条件载荷写入记忆与检索库以跨会话触发

    arXiv
    2507.10457
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    ChatGPT, Claude, LLaMA3 and others8
    Abstract作者定义 LPCI。

    作者把LPCI定义为针对智能体逻辑执行、记忆留存和工具集成的跨阶段漏洞类，而不是单次输入上的提示改写。

    Paper analysisRead analysis
You have reached the end