Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter5

Attack type

Jailbreaks5Prompt injection36Poisoning and backdoors12Extraction and theft4Detection evasion3Malicious use6

Defense type

Monitoring and auditing4

Impact

Harmful content3

System type

AI Agent5

Attacker access

Black-box3

Attack surface / entry point

User input5

Layer

Prompt layer29Model layer10Application layer5

System component

Memory3Guardrails and judges10Monitors4Permissions and sandboxing5Vision1Embeddings0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksLayer：Application layerSystem component：MonitorsSystem component：VisionSystem component：EmbeddingsClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  5. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end