Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter5

Attack technique

Gradient and representation optimization5Automated search28Encoding and obfuscation8Role-play and persuasion6Reasoning-chain manipulation3Defense-targeted6Dormant triggers14

System type

AI Agent3

Attack surface / entry point

Documents and messages2Tool responses2Code repositories and dependencies1

Layer

Application layer3

System component

Reasoning chains3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack technique：Reasoning-chain manipulationAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesAttack surface / entry point：Code repositories and dependenciesLayer：Application layerClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控

    arXiv
    2609.27542
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  3. AttacksarXiv 2603.12277

    Prompt injection is role confusion

    提出 CoT Forgery，经用户消息或工具输出注入伪造推理

    arXiv
    2603.12277
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    gpt-oss-20b, gpt-oss-120b, o4-mini and others11
    Abstract提示注入被作者解释为角色感知失败：听起来像某角色，就在表示里成为该角色。

    作者把提示注入解释成角色感知失败：标签划出的权限没有进入模型的内部几何。

    Paper analysisRead analysis
You have reached the end