Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Attack type

Prompt injection6

Attack technique

Gradient and representation optimization3Automated search14Multi-turn escalation1Encoding and obfuscation6Role-play and persuasion4Dormant triggers9

Impact

Output manipulation4

System type

LLM applications3AI Agent4

Attack surface / entry point

User input78Documents and messages4Tool responses7Tool and skill descriptions7Retrieval corpus4Memory writes3Inter-agent messages3Images, audio and video20Distribution channels5

Layer

Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Encoding and obfuscationAttack surface / entry point：Documents and messagesAttack surface / entry point：Inter-agent messagesClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.00392

    A2A-TIBA：针对 A2A 协议 LLM 智能体的间接提示注入攻击与三层同构攻防模型

    提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调

    arXiv
    2610.00392
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax-M3, deepseek-v4-pro, glm-5.3 and others8
    AbstractA2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。

    A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。

    Paper analysisRead analysis
  4. AttacksarXiv 2603.00131

    Thought Virus：多 Agent 系统中潜意识提示引发的病毒式失准

    提出 Thought Virus，经潜意识提示使偏好沿多 Agent 消息传播

    arXiv
    2603.00131
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
    AbstractThought Virus 把单点偏差传到下游。

    Thought Virus 把 subliminal prompting 放进多智能体通信，看单点偏差会不会在不点名目标概念时传到全网。

    Paper analysisRead analysis
  5. AttacksarXiv 2602.18514

    招聘中的特洛伊木马：标准模型与推理模型间接提示注入的红队测试案例研究

    用简历中的不可见指令做间接提示注入，操纵招聘推荐

    arXiv
    2602.18514
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen 3 30B A3B Instruct 2507, Qwen 3 30B A3B Thinking 2507

    Abstract作者称推理在简单注入下会帮攻击圆谎，在不合逻辑的复杂注入下又会把欺骗漏出来。

    Paper analysisRead analysis
  6. AttacksarXiv 2601.21360

    Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation

    提出 AST-ASIP ，把对抗指令植入编译器忽略区域以劫持代码评分

    arXiv
    2601.21360
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    DeepSeek-V3.2, Qwen3-235B, GPT-OSS-120B and others9
    Abstract作者称 RLHF 的服从性使评分脱离代码。

    这篇工作把自动代码评分中的失败称为 Compliance Paradox：评分模型可以离开提交逻辑，转而执行嵌在可编译代码里的隐藏指令。

    Paper analysisRead analysis
You have reached the end