Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Defense type

Model hardening7Detection and filtering1

Impact

Harmful content3Unauthorized actions23Output manipulation9Availability and reliability1

System type

AI Agent1coding agent0science agent0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringImpact：Availability and reliabilitySystem type：AI AgentSystem type：coding agentSystem type：science agentClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.03448

    Study retests 15 prompt injection detectors: benchmark scores poorly predict agent deployment performance

    重测提示注入检测器在 Agent 工具输出上的检出与任务阻断

    arXiv
    2610.03448
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Horizon-Labs, Wolf Defender, Prismor-1.5B and others15

    Abstract论文揭示公开基准无法反映智能体检测器表现，检测能力源于输入格式相似而非通用防御，建议基于工具输出与低误报评测。

    Paper analysisRead analysis
You have reached the end