Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

System type

Models and APIs1AI Agent28coding agent19Multi-agent systems1

Attack surface / entry point

User input295Documents and messages14Tool responses10Tool and skill descriptions4Code repositories and dependencies2Retrieval corpus6Memory writes6Inter-agent messages25Images, audio and video100Training data65Weights and gradients64Distribution channels14Inference services and hardware19
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：Multi-agent systemsAttack surface / entry point：Code repositories and dependenciesClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.31282

    基于区块链的 Agentic AI 框架：面向安全软件供应链的资源优化与能耗感知

    提出 AttestChain，将供应链安全智能体报告签名上链并据此控制发布

    arXiv
    2609.31282
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-class LLM
    AbstractAttestChain 将智能体报告与链上发布门控结合，现有证据来自受控合成构建的总体结果。

    AttestChain 是一个把 LLM 安全检查、智能体身份验证和许可链发布策略连接起来的软件供应链防御框架。。

    Paper analysisRead analysis
  2. 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
You have reached the end