Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

Attack technique

Gradient and representation optimization16Automated search60Multi-turn escalation8Encoding and obfuscation22Role-play and persuasion9Conversation structure manipulation5Reasoning-chain manipulation4Cross-modal payloads13Side channels0Defense-targeted20Dormant triggers34Selection manipulation12

System type

AI Agent3

Layer

Prompt layer10Application layer4Infrastructure layer4

System component

Reasoning chains4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Attack technique：Reasoning-chain manipulationAttack technique：Side channelsLayer：Application layerClear all

Another 247papers 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
  4. AttacksarXiv 2604.05549

    Stop obsessing over prompts: reasoning hijacking and constraint tightening for red-teaming LLM agents

    提出 JailAgent，不改用户提示，经推理劫持与记忆投毒操纵 Agent 动作

    arXiv
    2604.05549
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-3.5-turbo, GPT-4o, GPT-5 and others7
    AbstractJailAgent 不改提示词，用三阶段操纵推理与检索。

    JailAgent 是不修改用户原始提示词的 LLM 智能体红队框架。

    Paper analysisRead analysis
You have reached the end