Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter5

Attack type

Prompt injection4

Impact

Unauthorized actions4Output manipulation6

System type

Models and APIs2LLM applications15AI Agent10coding agent0Multi-agent systems4

Attack surface / entry point

User input38Documents and messages6Code repositories and dependencies4Retrieval corpus3Inter-agent messages10Images, audio and video43Training data30Weights and gradients14Distribution channels10Inference services and hardware6

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 248papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesClear all

Another 248papers 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. AttacksarXiv 2609.38270

    VirusCascade：劫持 LLM 推荐智能体的协同反思机制

    提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思

    arXiv
    2609.38270
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    AgentCF, AgentSEQ, AgentRAG and others4
    Abstract作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。

    VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。

    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
  5. 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
  6. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
You have reached the end