Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter5

Model risks

Deception and scheming3

Defense type

Monitoring and auditing5

Impact

Harmful content12Unauthorized actions23Data and privacy leaks9Output manipulation5Oversight failure37

System type

Models and APIs2LLM applications3AI Agent7coding agent3

Layer

Application layer7

System component

MCP and skills16Memory13Guardrails and judges6Monitors7Reasoning chains7Permissions and sandboxing11Fine-tuning and open weights8Vision3Audio3Image generation5Embeddings2Multimodal12
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.
Impact：Data and privacy leaksSystem type：Models and APIsSystem type：AI AgentSystem component：MonitorsSystem component：EmbeddingsClear all

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

  2. Risky behaviorarXiv 2609.32701

    研究显示前沿模型智能体在测试时自行形成隐蔽信道

    展示智能体在禁止泄露与独立监视下自发建立隐蔽信道传递机密

    arXiv
    2609.32701
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.6 Sol, Terra, Luna and others6
    Abstract论文研究了固定参数智能体在受监视交互中仅凭单比特反馈自发建立隐蔽信道，指出了多智能体跨域协作的保密安全新风险。

    论文研究了固定参数与提示词的智能体在受审计交互中自发形成隐蔽信道并泄露机密的过程。

    Paper analysisRead analysis
  3. 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. DefensesarXiv 2609.19587

    红队测试 Auto Mode：用注入与多上下文攻击绕过编码 Agent 阻断监控器

    提出 Auto Mode ++，加固编码 Agent 阻断监视器

    arXiv
    2609.19587
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Opus 5, Opus 4.8, Opus 4.7 and others8

    Abstract系统评估生产阻断监视器在面对持续恶意智能体时的表现，提出加固防御并指明多上下文防御挑战。

    Paper analysisRead analysis
  7. DefensesarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
  8. AttacksarXiv 2602.01757

    Zero2Text: Training-Free Cross-Domain Text Embedding Inversion Attack

    提出 Zero2Text，无需训练地跨域反演文本嵌入

    arXiv
    2602.01757
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GTR-Base, Qwen3-Embedding-0.6B, Text-Embedding-3-small and others4
    Abstract零训练在线对齐可在未知域、无泄漏对时从黑盒 embedding 还原句子。

    Zero2Text 是一种不训练 decoder、也不使用泄漏文本–向量对的文本 embedding 反演，针对 RAG 向量库在严格黑盒、目标域未知时的还原。

    Paper analysisRead analysis
You have reached the end