Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter2

System type

AI Agent59coding agent24Browser and computer use1Multi-agent systems3

Attack surface / entry point

Web pages and interfaces7Tool and skill descriptions1Images, audio and video3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 321papers have no tags yet and are not included in filtered results.
System type：Browser and computer useAttack surface / entry point：Tool and skill descriptionsClear all

Another 321papers 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
You have reached the end