Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5

Model risks

Dangerous agent actions3

Defense type

Monitoring and auditing7

Impact

Output manipulation3

System type

Models and APIs18LLM applications3AI Agent61coding agent20science agent3Browser and computer use4Multi-agent systems7

Layer

Model layer0Application layer7

System component

MCP and skills5Memory3RAG41Guardrails and judges35Monitors7Permissions and sandboxing4Vision14Audio3Image generation3Embeddings9Multimodal18
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.
System type：LLM applicationsSystem type：Browser and computer useLayer：Model layerLayer：Application layerSystem component：MonitorsClear all

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

  2. DefensesarXiv 2610.07570

    ProbeGuard：按共识形成过程判断弃答，识别医疗问答中的一致错误

    提出 ProbeGuard，按共识形成过程对医疗问答做选择性弃答

    arXiv
    2610.07570
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-8B, Llama-3.1-8B-Instruct, HuatuoGPT-o1-8B
    AbstractProbeGuard 用共识形成过程做可认证弃权，并在全票层分开答对与答错的共识。

    ProbeGuard 是给多轮共识医学问答用的认证弃权框架：基板照原样作答，弃权只看共识是怎么形成的。

    Paper analysisRead analysis
  4. 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
  6. Analysis and theoryarXiv 2609.07162

    论文：LLM 安全监控的监督缺口并非能力问题

    刻画单迹监控对跨执行超性质的监督缺口

    arXiv
    2609.07162
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Evaluated models
    Llama-3.1-8B, Mistral-24B, GPT-4o-mini and others9
    Abstract单迹监督的上界由 TV 决定。

    论文测量单迹安全监控相对 2-safety 超性质能看见多少：跨租户泄漏、觉察到被评估、策略性表现不佳都由两次执行之差定义，一条轨迹装不下判定。

    Paper analysisRead analysis
  7. DefensesarXiv 2609.04159

    Sentinel-RL：将拓扑推理从 LLM 智能体中卸载到安全运营中心

    提出 Sentinel-RL，将拓扑处置从 LLM 卸载到受约束图策略

    arXiv
    2609.04159
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    HetGAT, PPO
    AbstractSentinel-RL 用图编码器与 PPO 承担拓扑决策，LLM 负责叙述与门控，并在 LANL 上报告检测与时延。

    Sentinel-RL 是面向 SOC 的神经符号架构：拓扑决策离开 LLM，改由认证图上的 HetGAT 与 PPO 完成。

    Paper analysisRead analysis
You have reached the end