Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter5

System type

AI Agent7coding agent1Browser and computer use1Multi-agent systems0

Attack surface / entry point

User input3Web pages and interfaces2Tool and skill descriptions22Inter-agent messages4Distribution channels17

System component

MCP and skills2Monitors3Permissions and sandboxing3Vision3Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：Browser and computer useSystem type：Multi-agent systemsAttack surface / entry point：Web pages and interfacesSystem component：MCP and skillsClear all

Another 255papers 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
  2. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
You have reached the end