Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack type

Jailbreaks43Prompt injection25Poisoning and backdoors19Extraction and theft2Detection evasion21

Attack technique

Automated search6Encoding and obfuscation1Role-play and persuasion3Side channels4Defense-targeted1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack technique：Encoding and obfuscationAttack technique：Defense-targetedClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.10117

    研究揭示基于混淆的端侧 LLM 保护方案的安全边界

    提出 Collapse，从端侧混淆暴露视图抽取高效用替代模型

    arXiv
    2609.10117
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    BERT-Base, ViT-Base, Qwen2.5-0.5B and others4
    AbstractOprior 是四原语复合的安全边界，Collapse 利用列方向泄漏抽取替代模型，Oext 只被同一攻击评测。

    这篇工作用代数原语统一若干 TEE 卸载混淆，给出该族的典范边界，再说明该边界挡不住一种分阶段模型抽取。。

    Paper analysisRead analysis
  2. AttacksarXiv 2604.01039

    评估与加固 LLM 系统指令以抵御编码攻击提取

    用编码与结构化请求抽取系统指令，并用 CoT 改写加固

    arXiv
    2604.01039
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4.1-mini, GPT-3.5-turbo, Gemini-2.5-flash and others7
    Abstract编码式请求可在直接拒答后引出系统指令。

    这项工作评测并加固 LLM 系统指令在编码式抽取下的保密性。作者关心的是：直接抽取已被拒绝时，把同一请求改写成格式化或编码任务，模型是否仍交出受保护内容。

    Paper analysisRead analysis
You have reached the end