Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter5

Attack type

Jailbreaks1Prompt injection13Poisoning and backdoors36

Attack technique

Gradient and representation optimization0Dormant triggers1

Attack surface / entry point

User input16Memory writes1Images, audio and video6Training data0Weights and gradients3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 203papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack technique：Gradient and representation optimizationAttack technique：Dormant triggersAttack surface / entry point：Memory writesAttack surface / entry point：Training dataClear all

Another 203papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2606.09084

    研究者提出 Context-Fractured Decomposition 攻击

    提出 CFD 跨会话分解攻击，利用工件来源缺口绕过工具型 Agent 的本地检查

    arXiv
    2606.09084
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4.1, GPT-5-nano, Claude-3.5-Sonnet and others6
    AbstractCFD 用无指令 artifact 把越狱拆到跨会话。

    CFD针对工具型 LLM 智能体：利用 artifact 来源不被跟踪这一部署失败模式，把有害目标拆开后延迟组合。

    Paper analysisRead analysis
You have reached the end