Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Defense type

Inference-time intervention6Detection and filtering3Instruction–data separation2Permissions and approval5Monitoring and auditing55

Layer

Model layer0Application layer2

System component

MCP and skills12Memory10Monitors2Permissions and sandboxing23Vision3Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationLayer：Model layerLayer：Application layerSystem component：MonitorsClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.19587

    红队测试 Auto Mode：用注入与多上下文攻击绕过编码 Agent 阻断监控器

    提出 Auto Mode ++，加固编码 Agent 阻断监视器

    arXiv
    2609.19587
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Opus 5, Opus 4.8, Opus 4.7 and others8

    Abstract系统评估生产阻断监视器在面对持续恶意智能体时的表现，提出加固防御并指明多上下文防御挑战。

    Paper analysisRead analysis
  2. DefensesarXiv 2601.05755

    VIGIL: defending LLM agents against tool-flow injection with "verify before submit"

    提出 VIGIL 先验证后提交，防御 Agent 工具流注入

    arXiv
    2601.05755
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3-max, Gemini-2.5-pro
    AbstractVIGIL 用意图约束下的提交前验证处理工具流注入。

    VIGIL 用 verify-before-commit 处理智能体的工具流注入，并配有基准 SIREN。

    Paper analysisRead analysis
You have reached the end