Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter1

Attack technique

Gradient and representation optimization3Automated search8Multi-turn escalation6Encoding and obfuscation14Role-play and persuasion5Cross-modal payloads7Defense-targeted3Dormant triggers6

System component

Guardrails and judges3
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：Defense-targetedClear all

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

  1. Evaluation and benchmarksarXiv 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
  2. Evaluation and benchmarksarXiv 2608.16246

    CompoSkill 框架利用逐个通过扫描的 Agent 技能组合发起攻击

    提出 CompoSkill，将逐个通过扫描的技能编排为攻击链

    arXiv
    2608.16246
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Gemini-3.1-flash, DeepSeek-V4 and others4

    Abstract论文分析了智能体技能组合风险，指出单包安全认证状态不具备可组合性，需转向路径级防护。

    Paper analysisRead analysis
You have reached the end