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

Attack type

Jailbreaks61Prompt injection9Extraction and theft2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Extraction and theftTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2610.03434

    Persona Guardrail：面向智能体系统的生产级防御框架

    提出 Persona Guardrail，强制客服智能体守住功能边界

    arXiv
    2610.03434
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    Qwen3-30B-A3B, Qwen3-VL-30B, Qwen3-8B and others5
    AbstractPersona Guardrail 用功能边界做同步输入输出校验，并在 PAGE 与生产延迟预算下给出评测。

    Persona Guardrail 是客服向智能体的同步运行时防御：先写明功能边界，再决定放行或拦截，而不是只检测某一攻击类。

    Paper analysisRead analysis
  2. 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