Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Prompt injection3

Impact

Output manipulation3

System type

Models and APIs1LLM applications3AI Agent28coding agent9web agent3Multi-agent systems3

Attack surface / entry point

User input63Documents and messages4Tool responses3Code repositories and dependencies0Inter-agent messages7Images, audio and video16Training data6

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesClear all

Another 233papers 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. 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
  3. Evaluation and benchmarksarXiv 2609.17320

    Emergence World：对长时程多智能体系统开展对抗压力测试

    提出 Emergence World，对长时程多智能体系统开展对抗压力测试

    arXiv
    2609.17320
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9

    Abstract作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2607.24177

    EXE-Bench：为真实可用性对 AI Windows 恶意软件检测器进行权衡排名

    提出 EXE-Bench 比较 Windows 恶意软件检测器的可用性权衡

    arXiv
    2607.24177
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    EmberGBDT, BBDnn, BBDnnFDRS and others15
    Abstract统一四指标后，手工特征的 EmberGBDT 综合居首，只看准确率会误导部署。

    EXE-Bench 用同一设置给 AI Windows 恶意软件检测器做四指标排序，而不是只比一次测试集准确率。。

    Paper analysisRead analysis
You have reached the end