Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Attack type

Prompt injection3

Impact

Unauthorized actions3

System type

LLM applications3AI Agent129coding agent10web agent4Browser and computer use3Multi-agent systems10

Attack surface / entry point

Web pages and interfaces7Tool responses2Memory writes1Images, audio and video3

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
System type：Browser and computer useAttack surface / entry point：Tool responsesAttack surface / entry point：Memory writesLayer：Application layerClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.03089

    COBRA：为计算机使用 Agent 防御分支引导攻击的双 LLM 架构

    提出 COBRA 双 LLM 架构，防御计算机使用 Agent 的分支转向攻击

    arXiv
    2610.03089
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    gpt-5, UI-TARS-1.5-7B, claude-sonnet-5 and others6

    Abstract提出分支转向防御架构 COBRA，通过事前能力约束与边界代理消除分支转向攻击并兼顾效用。

    Paper analysisRead analysis
  3. 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
You have reached the end