Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 1 paper
Filter3

System type

AI Agent23coding agent4Browser and computer use1Multi-agent systems7

Attack surface / entry point

Tool and skill descriptions1Inter-agent messages0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：Browser and computer useAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Inter-agent messagesTopic: Agent safetyClear all
  1. DefensesarXiv 2610.03089

    COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks

    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