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 technique

Gradient and representation optimization0Multi-turn escalation0Conversation structure manipulation1

Defense type

Inference-time intervention1

Layer

Model layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Multi-turn escalationAttack technique：Conversation structure manipulationDefense type：Inference-time interventionLayer：Model layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2603.08234

    The Continuation vs. Refusal Debate: Mechanism Analysis of Continuation-Triggered Jailbreaks in Large Language Models

    Analyzing the attention head mechanism of continuation-triggered jailbreaks and proposing 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