Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

Attack type

Prompt injection4

Attack technique

Automated search12Encoding and obfuscation4Role-play and persuasion4Dormant triggers8

Impact

Output manipulation3

System type

LLM applications3AI Agent1coding agent0

Attack surface / entry point

User input8Documents and messages4Tool responses4Tool and skill descriptions5Retrieval corpus4Memory writes3Distribution channels5

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 248papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationSystem type：LLM applicationsSystem type：AI AgentSystem type：coding agentAttack surface / entry point：Documents and messagesClear all

Another 248papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. 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