Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter5

Attack technique

Gradient and representation optimization0Automated search10Encoding and obfuscation4Reasoning-chain manipulation1Defense-targeted11Dormant triggers3Selection manipulation1

Layer

Prompt layer4Application layer2

System component

MCP and skills10RAG7Guardrails and judges2Reasoning chains6Vision7Embeddings3Multimodal8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Reasoning-chain manipulationAttack technique：Selection manipulationLayer：Application layerSystem component：Guardrails and judgesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描

    arXiv
    2609.30383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
You have reached the end