Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

System type

Models and APIs1AI Agent28coding agent19Browser and computer use1

Attack surface / entry point

User input288Web pages and interfaces7Documents and messages10Tool responses7Code repositories and dependencies2Retrieval corpus3Images, audio and video104Training data64Weights and gradients66Distribution channels17Inference services and hardware18
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：Browser and computer useAttack surface / entry point：Code repositories and dependenciesClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链

    arXiv
    2608.09867
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。

    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