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 injection5Poisoning and backdoors4

Impact

Unauthorized actions10Data and privacy leaks4Output manipulation6

System type

LLM applications15AI Agent17coding agent0Multi-agent systems6

Attack surface / entry point

User input7Documents and messages4Code repositories and dependencies4Memory writes2Inter-agent messages10Distribution channels4

Layer

Application layer6

System component

Memory4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesAttack surface / entry point：Memory writesClear all

Another 255papers 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
  4. 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
  5. 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
  6. AttacksarXiv 2601.00240

    When agents view humans as out-group: belief-dependent bias in LLM-driven agents

    提出 BPA 改写 profile 与记忆，重新诱发智能体对人类的外群体偏向

    arXiv
    2601.00240
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-4o-mini
    Abstract最小群体线索下出现内群体偏向。

    作者考察 LLM 智能体在任意群体边界下会不会把人类当外群体，并用信念投毒检验面向人类的抑制是否依赖身份信念。

    Paper analysisRead analysis
You have reached the end