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

Jailbreaks50Extraction and theft1

System type

Models and APIs1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Extraction and theftSystem type：Models and APIsTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2609.19325

    AUDITPLAN：先提交安全计划再作答的可审计安全对齐方法

    提出 AUDIT PLAN 先计划后作答，并用 FAITHGATE 绑定答案奖励与计划正确性

    arXiv
    2609.19325
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen-3-4B-Instruct and others4
    Abstract先承诺可机检安全计划，再让计划正确性决定能否拿到答案奖励。

    AUDIT PLAN 把安全对齐从“只优化最终答案”改成“先提交隐藏的结构化安全计划，再按该计划作答”，并用 FAITHGATE 把高答案奖励限定在计划正确时。

    Paper analysisRead analysis
You have reached the end