Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter5

System type

LLM applications3AI Agent88coding agent41Browser and computer use2Multi-agent systems4

Attack surface / entry point

Web pages and interfaces7Tool and skill descriptions1Code repositories and dependencies1Images, audio and video3

Layer

Model layer0Application layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
System type：Browser and computer useAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Code repositories and dependenciesLayer：Model layerLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  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
  2. Evaluation and benchmarksarXiv 2604.02947

    AgentHazard：评估计算机使用智能体有害行为的基准

    提出 AgentHazard 基准，评测计算机使用智能体的执行层有害行为

    arXiv
    2604.02947
    Published
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen2.5-72B-Instruct, Qwen2.5-Coder-32B-Instruct, Qwen3-32B and others12
    AbstractAgentHazard 评估了计算机使用智能体的执行安全，作者认为模型层对齐无法可靠保障智能体层面的安全性。

    AgentHazard 是针对计算机使用智能体执行层安全构建的评估基准，重点探究多步工具调用下局部合理动作累积引发的危害。

    Paper analysisRead analysis
You have reached the end