Skip to content

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

Oct 13 · Tuesday

All papers

Found 4 papers
Filter5

Defense type

Detection and filtering3

System type

Models and APIs16LLM applications45AI Agent46coding agent7science agent4web agent4Multi-agent systems5

Layer

Model layer0Application layer4

System component

RAG3Guardrails and judges4Permissions and sandboxing3Vision7Embeddings0Multimodal7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
System type：web agentLayer：Model layerLayer：Application layerSystem component：Guardrails and judgesSystem component：EmbeddingsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2604.06240

    研究者开源 Universal Verifier 与 CUAVerifierBench，用于验证计算机使用 Agent 轨迹

    构建 Universal Verifier 核验计算机使用 Agent 轨迹

    arXiv
    2604.06240
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.2, GPT-4o, o4-mini and others8
    Abstract四条设计原则叠成 Universal Verifier，作者称其与人类一致程度相当且假阳性近零。

    Universal Verifier 给计算机使用轨迹打过程分和结果分，并定位失败。CUAVerifierBench 用人工标签衡量这种验证器。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end