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

Jailbreaks1

Impact

Harmful content45Unauthorized actions3Output manipulation3Oversight failure1

System component

Guardrails and judges1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksImpact：Oversight failureSystem component：Guardrails and judgesClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.00498

    SEAV：面向大语言模型越狱评测的有效性验证框架

    提出 SEAV，逐步核验越狱回复的事实与操作有效性

    arXiv
    2609.00498
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    AbstractSEAV 用逐步检索和依赖检查重判越狱成功，SD-A 与三个基准上的原成功标签都有一批被改判。

    SEAV 是一层生成后的越狱评测：回复要相关、事实正确、顺序合规，并且在操作上足以推进有害意图，才算成功。。

    Paper analysisRead analysis
You have reached the end