Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter6

Attack type

Jailbreaks7Prompt injection99Poisoning and backdoors49Extraction and theft2Detection evasion10

System type

Models and APIs1AI Agent1

Attack surface / entry point

User input45Documents and messages0Code repositories and dependencies1Memory writes1Inter-agent messages3Images, audio and video4Training data7Weights and gradients12Inference services and hardware8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftSystem type：Models and APIsSystem type：AI AgentAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Memory writesClear all

Another 201papers 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 2608.03272

    多智能体协同过滤系统的连接性攻击与防御研究

    复现 AgentCF 上的多智能体攻防并刻画连通性作用

    arXiv
    2608.03272
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
    Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。

    作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。

    Paper analysisRead analysis
You have reached the end