Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter2

Attack type

Prompt injection2

System component

MCP and skills17Memory10Guardrails and judges4Monitors4Permissions and sandboxing41Multimodal2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Prompt injectionSystem component：MultimodalTopic: Agent safetyClear all
  1. DefensesarXiv 2603.14707

    视觉混淆代理：利用与防御计算机使用智能体的感知失效

    提出进程外双通道对比分类，拦截计算机使用智能体的错误点击

    arXiv
    2603.14707
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    multi-modal-embed-small
    Abstract感知错误可被屏幕像素对调利用。

    作者把 CUA 的感知失败写成安全漏洞visual confused deputy：智能体按看错的屏幕授权 click(x,y)，真实落点与它以为的元素不一致。

    Paper analysisRead analysis
  2. DefensesarXiv 2602.10915

    Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

    提出 Aura，用可信内核中介移动 Agent 的身份、感知与动作控制

    arXiv
    2602.10915
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Gemini-3-Flash
    AbstractAura 以 Agent Kernel 中介结构化交互。

    Aura 用内核中介的结构化智能体交互，替换以屏幕为接口的移动助手。。

    Paper analysisRead analysis
You have reached the end