Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Malicious use3

Model risks

Deception and scheming3

Impact

Oversight failure3

System type

AI Agent3coding agent1science agent0

Attack surface / entry point

User input3

Layer

Application layer3

System component

Monitors3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：Malicious useModel risks：Deception and schemingSystem type：AI AgentSystem type：coding agentSystem type：science agentClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  2. 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
  3. DefensesarXiv 2604.11806

    Meerkat：跨大量 Agent 轨迹检测安全违规

    提出 Meerkat，聚类并搜索 Agent 轨迹库以定位跨轨迹安全违规

    arXiv
    2604.11806
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4-mini, Qwen3.5-397B-A17B and others5
    AbstractMeerkat 用聚类与智能体搜索定位跨轨迹违规，并在真实评测轨迹中找出脚手架泄题与奖励黑客。

    Meerkat 是事后审计方法，用来在智能体轨迹仓库里找出单条看不出、合在一起才违反自然语言安全属性的见证。

    Paper analysisRead analysis
You have reached the end