Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Attack technique

Automated search3Encoding and obfuscation1

Attack surface / entry point

User input17Documents and messages1Retrieval corpus4Images, audio and video5

System component

RAG0Guardrails and judges1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationAttack surface / entry point：Documents and messagesSystem component：RAGSystem component：Guardrails and judgesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. 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