Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Prompt injection5

Impact

Output manipulation3

System type

Models and APIs3LLM applications23AI Agent11coding agent0Multi-agent systems3

Attack surface / entry point

User input309Web pages and interfaces5Documents and messages19Tool responses16Tool and skill descriptions26Code repositories and dependencies21Retrieval corpus6Memory writes10Inter-agent messages24Images, audio and video99Training data67Weights and gradients65Distribution channels35Inference services and hardware18

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Retrieval corpusClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.39146

    MADBench：多智能体辩论安全性评测基准发布

    提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响

    arXiv
    2609.39146
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-4o, GPT-5, GPT-6 Astra
    AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。

    MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2609.37737

    研究用因果激活修补定位模型服从提示注入指令的决策层

    用因果激活修补定位模型服从提示注入的决策层

    arXiv
    2609.37737
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Qwen3-14B, Qwen3-32B and others7
    Abstract合规的因果杠杆集中在网络后三分之一的低秩子空间，该层也是混淆下检测最好的位置。

    这篇工作用逐层激活修补定位提示注入合规发生在网络何处，并把该位置用于检测验证。。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.24662

    DUMA-Bench：评估 LLM Agent 安全的双控多智能体基准

    提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反

    arXiv
    2609.24662
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5, GPT-5-mini, GPT-5-nano and others14
    AbstractDUMA-Bench 用双控交互评测智能体安全。

    DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.17648

    多智能体 LLM 流水线中的信任传播与结构隔离

    用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行

    arXiv
    2609.17648
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gemma4:31b-cloud
    Abstract结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。

    作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。

    Paper analysisRead analysis
  5. AttacksarXiv 2606.06244

    研究者提出 Ghostwriter 攻击：用伪造证据注入操纵 LLM 观点

    提出 Ghostwriter 攻击，用伪权威证据条件注入操纵模型观点

    arXiv
    2606.06244
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude-3.7-Sonnet, DeepSeek-V3 and others10
    Abstract作者称攻击未被消除。

    Ghostwriter 是一种针对上下文窗口的观点引导攻击：把误导陈述改写成伪权威文本，再在相关查询中让目标模型把该观点写进回答。

    Paper analysisRead analysis
  6. AttacksarXiv 2602.01757

    Zero2Text: Training-Free Cross-Domain Text Embedding Inversion Attack

    提出 Zero2Text，无需训练地跨域反演文本嵌入

    arXiv
    2602.01757
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GTR-Base, Qwen3-Embedding-0.6B, Text-Embedding-3-small and others4
    Abstract零训练在线对齐可在未知域、无泄漏对时从黑盒 embedding 还原句子。

    Zero2Text 是一种不训练 decoder、也不使用泄漏文本–向量对的文本 embedding 反演，针对 RAG 向量库在严格黑盒、目标域未知时的还原。

    Paper analysisRead analysis
You have reached the end