Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 1 paper
Filter2

Attack type

Model tampering1

System component

Fine-tuning and open weights1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Model tamperingSystem component：Fine-tuning and open weightsTopic: 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
You have reached the end