Skip to content

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

Oct 13 · Tuesday

Defenses and guardrails · Papers

Found 4 papers
Filter1

Attack type

Jailbreaks4

Defense type

Detection and filtering4

System type

AI Agent4

Attack surface / entry point

User input4

Layer

Prompt layer3Application layer4

System component

Guardrails and judges4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Application layerTopic: Defenses and guardrailsClear all
  1. Evaluation and benchmarksarXiv 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
  3. Evaluation and benchmarksarXiv 2601.10156

    ToolSafe 提出步骤级护栏 TS-Guard 与 TS-Flow，降低 Agent 有害工具调用

    提出 TS-Guard 与 TS-Flow，在执行前检测并引导 Agent 修正有害工具调用

    arXiv
    2601.10156
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, TS-Guard, Qwen2.5-14B-Instruct
    AbstractTS-Bench 标步骤级风险，TS-Guard 用多任务 RL 做执行前判定，TS-Flow 用反馈代替直接中止。

    ToolSafe 研究 LLM 智能体在工具执行前的步骤级安全：基准 TS-Bench、护栏 TS-Guard，以及反馈驱动框架 TS-Flow。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end