Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 2 papers
Filter1

Layer

Model layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Model layerTopic: Defenses and guardrailsClear all
  1. InterpretabilityarXiv 2609.06934

    论文提出拒答的几何解释：事后安全训练脆弱，预训练期持续安全共训更抗攻击

    解释后验安全的权重几何脆弱性，并提出预训练持续安全共训练

    arXiv
    2609.06934
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-7B-Instruct, Llama-3-8B and others15

    Abstract论文将后验安全脆弱性归因于正交抑制，并提出通过预训练持续共训练实现具备微调抗性的安全防护。

    Paper analysisRead analysis
  2. 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