Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack technique

Gradient and representation optimization4Automated search28Encoding and obfuscation8Role-play and persuasion3Conversation structure manipulation3Cross-modal payloads5Defense-targeted9Dormant triggers11Selection manipulation10

Attack surface / entry point

User input11Web pages and interfaces1Tool and skill descriptions1Code repositories and dependencies1

Layer

Prompt layer2Application layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Attack technique：Conversation structure manipulationAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Code repositories and dependenciesLayer：Prompt layerLayer：Application layerClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链

    arXiv
    2608.09867
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。

    Paper analysisRead analysis
  3. AttacksarXiv 2605.24421

    研究者提出日志型提示注入攻击，可抑制 SOC 中 LLM 分析助手的恶意日志识别

    提出日志基底提示注入，操纵 SOC 分析员的分类、摘要与处置建议

    arXiv
    2605.24421
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    gpt-4o-mini

    Abstract在 gpt-4o-mini 上，人格劫持与上下文操纵可改写 SOC 分析输出，直接覆盖在分类上无效。

    Paper analysisRead analysis
You have reached the end