Skip to content

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

Oct 13 · Tuesday

All papers

Found 10 papers
Filter4

Attack type

Prompt injection10

Impact

Unauthorized actions5Output manipulation4

System type

LLM applications18AI Agent62coding agent5web agent4Multi-agent systems6

Attack surface / entry point

User input15Web pages and interfaces24Documents and messages10Tool responses8Tool and skill descriptions4Retrieval corpus4Memory writes7Inter-agent messages25Images, audio and video4

Layer

Application layer10
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
System type：web agentSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesLayer：Application layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. 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
  4. 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
  6. 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
  7. AttacksarXiv 2605.08310

    WebTrap：针对浏览器 Agent 导航过程的中途劫持注入攻击

    提出 WebTrap 三阶段陷阱，中途劫持浏览器 Agent 完成攻击后再返回用户任务

    arXiv
    2605.08310
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    DeepSeek-V3.1-Terminus, Gemini-2.5-Flash, GLM-4.5-Air and others5
    AbstractWebTrap 把攻击目标嵌进用户流程中途执行再返回。

    WebTrap 是针对长程网页与文件导航的中途劫持注入，目标是在完成攻击动作后仍回到用户任务。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.04474

    From Spark to Wildfire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

    Proposing a lineage-graph governance layer to suppress error cascades in multi-agent collaboration

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractA single seed can solidify into a false consensus along a fixed collaboration graph.

    The authors turn "small errors becoming collective false consensus" in LLM-MAS into a measurable propagation on a graph, and use a plug-in that only changes messages, not topology, to reduce the final infection.

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2512.23128

    牛津等发布 TRAP 基准

    构建 TRAP 基准，评测网页 Agent 被界面提示注入劫持任务的情况

    arXiv
    2512.23128
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5, Claude Sonnet 3.7, Gemini 2.5 Flash and others6
    Abstract论文提出了基于五维模块化攻击空间的 TRAP 基准，评估了六个模型在真实网页环境中的注入风险。

    研究定位：针对网页自主智能体易受外部界面提示注入攻击的问题，构建了基于真实网站克隆的模块化评测基准 TRAP。

    Paper analysisRead analysis
  10. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end