Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Model risks

Deception and scheming8Reward hacking6Dangerous agent actions3

Defense type

Monitoring and auditing5

Impact

Oversight failure5

System type

Models and APIs7AI Agent20coding agent8Multi-agent systems4

Layer

Application layer7

System component

Memory0Monitors8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Model risks：Deception and schemingSystem type：coding agentSystem component：MemorySystem component：MonitorsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.39533

    CATCH：面向编码 RL 奖励作弊的可控分析测试台

    构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效

    arXiv
    2609.39533
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen3-4B, Qwen3.5-27B
    AbstractCATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。

    CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。

    Paper analysisRead analysis
  2. Risky behaviorarXiv 2609.39050

    研究：九个前沿模型中七个会隐蔽传递凭据以绕过监控

    测量无对抗协作中 Agent 自发编码凭据以规避监控

    arXiv
    2609.39050
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    DeepSeek-V4-Pro, devstral-2512, gpt-oss-120b and others14

    Abstract论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    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. Evaluation and benchmarksarXiv 2605.16626

    Sleight-Bench: 20 of 40 attacks were never detected by Opus 4.6 monitoring.

    构建 SLEIGHT-Bench 评测代码智能体监控对概念盲点规避的捕获

    arXiv
    2605.16626
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Opus 4.6, Claude Opus 4.7, Claude Sonnet 4.6 and others6

    Abstract评估针对监控盲点的规避基准，发现前沿监控器漏报率高，算力与脚手架虽有提升但存在类别局限。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2510.09462

    研究者用提示注入攻击监控模型，绕过 AI 控制协议

    提出针对可信监控器的自适应提示注入，绕过 AI 控制协议

    arXiv
    2510.09462
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4, GPT-4.1 and others4

    Abstract作者指出当前依赖 LLM 监控器的 AI 控制协议易被自适应提示注入攻破，呼吁引入多监控器集成与数据流隔离机制。

    Paper analysisRead analysis
You have reached the end