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 technique

Role-play and persuasion1Defense-targeted6Dormant triggers14

Attack surface / entry point

Documents and messages0Training data1

Layer

Application layer4Training and data layer1
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 technique：Role-play and persuasionAttack surface / entry point：Documents and messagesAttack surface / entry point：Training dataLayer：Training and data layerClear all

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

  1. AttacksarXiv 2601.22169

    In Vino Veritas and Vulnerabilities：用醉酒语言诱导检验 LLM 安全

    用醉酒语言诱导改编对话模型并评测越狱与隐私泄露

    arXiv
    2601.22169
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA2-7B, LLaMA3-8B, Mistral-7B and others5
    Abstract醉酒语言诱导在五个 LLM 上抬高越狱与部分隐私错误，作者将其视为攻击向量。

    作者把醉酒语言当作攻击向量，检验把 LLM 适配成醉酒发短信的模式后，越狱和情境隐私是否变差。动机是人类醉酒时的失范与泄密，以及 LLM 模拟人设的能力。

    Paper analysisRead analysis
You have reached the end