Skip to content

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

Oct 13 · Tuesday

All papers

Found 9 papers
Filter6

Attack type

Prompt injection5Poisoning and backdoors5

Attack technique

Gradient and representation optimization6Automated search31Multi-turn escalation7Encoding and obfuscation12Role-play and persuasion7Conversation structure manipulation4Reasoning-chain manipulation3Cross-modal payloads4Defense-targeted12Dormant triggers21Selection manipulation3

Impact

Output manipulation6

System type

LLM applications4AI Agent5

Attack surface / entry point

User input6Web pages and interfaces5Documents and messages2Tool responses3Tool and skill descriptions10Retrieval corpus6Images, audio and video6Weights and gradients1Distribution channels9

Layer

Prompt layer15Model layer10Application layer9
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.
Attack technique：Gradient and representation optimizationAttack technique：Selection manipulationAttack surface / entry point：User inputAttack surface / entry point：Documents and messagesAttack surface / entry point：Weights and gradientsLayer：Application layerClear all

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

  1. AttacksarXiv 2610.12524

    An exploration of attacks on AI agent systems

    Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection

    arXiv
    2610.12524
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
    AbstractSingle-agent filtering and classification can be bypassed by format or wording, and A2A card selection is also biased toward names and descriptions.

    The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.

    Paper analysisRead analysis
  3. AttacksarXiv 2609.39788

    研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

    提出只训练或篡改多智能体潜在通信链路来提高有害遵从

    arXiv
    2609.39788
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
    Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。

    学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。

    Paper analysisRead analysis
  6. AttacksarXiv 2606.12716

    PaperGuard：针对多模态 AI 同行评审的攻击与防御基准

    提出 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令

    arXiv
    2606.12716
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
    AbstractPaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。

    PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。

    Paper analysisRead analysis
  9. AttacksarXiv 2602.00364

    "Someone hid it": Query-agnostic black-box attacks against LLM retrieval

    提出查询无关黑盒攻击 DQ-A，用可迁移文末后缀降低文档检索排名

    arXiv
    2602.00364
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen-1.5-7B-Instruct, SFR-Embedding-Mistral, E5-Mistral-7B-Instruct and others10
    AbstractDQ-A 以无查询黑盒后缀压低 LLM 检索排名，并在 BRIGHT 上比较三种基线。

    DQ-A 是一种 query-agnostic、complete black-box 的文档隐藏攻击，对象是用最后隐层相似度匹配的 LLM 检索。

    Paper analysisRead analysis
You have reached the end