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

Gradient and representation optimization11Conversation structure manipulation1Defense-targeted7Dormant triggers3

System type

Models and APIs1science agent0

Layer

Prompt layer9Model layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack technique：Conversation structure manipulationSystem type：Models and APIsSystem type：science agentLayer：Model layerClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2603.08234

    续写与拒答之争：大语言模型中续写触发越狱的机制分析

    分析续写触发越狱的注意力头机制并提出 HCS

    arXiv
    2603.08234
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
    Abstract作者称越狱来自两类头竞争，HCS 加蒸馏可把该竞争用于推理时干预。

    作者用注意力头机制分析 continuation-triggered jailbreak：同一有害指令下，把 continuation 后缀从指令后面挪到提示词边界外，模型更容易顺着后缀继续生成。

    Paper analysisRead analysis
You have reached the end