Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter3

Attack type

Prompt injection5Poisoning and backdoors3Malicious use3

Model risks

Deception and scheming5Reward hacking2Misalignment and value divergence4Dangerous agent actions5Inappropriate refusal9Hallucination and fabrication6

Defense type

Monitoring and auditing4

Impact

Unauthorized actions5

System type

AI Agent7

Attack surface / entry point

User input7Web pages and interfaces4Tool responses6Code repositories and dependencies3Memory writes3

Layer

Application layer7

System component

Monitors5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Reward hackingModel risks：Dangerous agent actionsAttack surface / entry point：User inputClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    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 2609.22724

    MATE：面向移动 Agent 的策略感知安全审计方法

    提出移动 Agent 轨迹审计器 MATE，判断轨迹是否违反可编辑安全策略

    arXiv
    2609.22724
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Attacker
    Black-box
    Evaluated models
    MATE-0.5B, MATE-1.5B, MATE-3B
    AbstractMATE 用合成轨迹微调轻量审计器，在可编辑策略下判断移动智能体轨迹是否违规并给出解释。

    MATE 是面向移动 GUI 智能体的轻量策略条件轨迹审计器，在给定自然语言安全策略时判断轨迹是否违规并解释原因。

    Paper analysisRead analysis
  7. 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