Skip to content

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

Oct 13 · Tuesday

All papers

Found 8 papers
Filter5

Attack type

Prompt injection8

Attack technique

Gradient and representation optimization6Automated search15Encoding and obfuscation7Role-play and persuasion5Cross-modal payloads6Defense-targeted1Dormant triggers10

Impact

Output manipulation5

System type

LLM applications5AI Agent3

Attack surface / entry point

User input17Web pages and interfaces4Documents and messages5Tool responses7Tool and skill descriptions11Code repositories and dependencies4Retrieval corpus4Memory writes5Distribution channels11

Layer

Application layer8

System component

Guardrails and judges3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 218papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationAttack technique：Defense-targetedAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesLayer：Application layerClear all

Another 218papers 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 2609.22510

    特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse

    arXiv
    2609.22510
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
  4. 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
  5. AttacksarXiv 2602.05484

    Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection

    提出隐蔽提示注入攻击 LLM 钓鱼检测器，并给出防御 InjectDefuser

    arXiv
    2602.05484
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    OpenAI GPT-5, xAI Grok 4 Fast (Non-Reasoning), Meta Llama 4 Maverick and others4
    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