Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack type

Jailbreaks7Prompt injection1

Defense type

Instruction–data separation0Permissions and approval0Monitoring and auditing1

Layer

Model layer1Application layer72
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：Prompt injectionDefense type：Instruction–data separationDefense type：Permissions and approvalDefense type：Monitoring and auditingLayer：Model layerClear all

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

  1. DefensesarXiv 2610.02413

    研究：分类后缀可提升激活探针的分布外恶意输入检测

    用分类后缀提升激活探针对分布外恶意输入的检测

    arXiv
    2610.02413
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B, Qwen3.5-9B, Gemma-4-12B
    Abstract作者称排序增益来自分类格式，低 FPR 精度来自点名准则。

    用户轮后的分类后缀，被作者用作激活探针的分布外检测干预：排序看格式，低 FPR 精度看是否点名恶意/良性。

    Paper analysisRead analysis
You have reached the end