Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Prompt injection3

Attack technique

Gradient and representation optimization3Automated search3Cross-modal payloads3

Impact

Unauthorized actions3

System type

AI Agent3

Attack surface / entry point

User input8Web pages and interfaces3Documents and messages5Tool responses11Tool and skill descriptions12Code repositories and dependencies3Distribution channels7

Layer

Application layer3
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.
Attack technique：Automated searchImpact：Unauthorized actionsAttack surface / entry point：Web pages and interfacesClear all

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

  1. AttacksarXiv 2610.08951

    ASPIRE：面向 LLM Agent 的开放式提示注入红队引擎

    提出 ASPIRE 行为图搜索，开放式发现 Agent 提示注入漏洞

    arXiv
    2610.08951
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini-3.7-Flash, DeepSeek-V4-Flash, Gemini-2.5-flash
    AbstractASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。

    ASPIRE 是给搭建方用的智能体提示注入红队引擎，目标是开放式画出可利用的行为路径，而不是在固定任务上打磨一条载荷。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.33628

    用课程强化学习对前沿模型做提示注入红队测试

    用跨目标课程强化学习训练提示注入红队，攻破前沿智能体

    arXiv
    2609.33628
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o-mini, GPT-5-nano, GPT-5.6-Luna and others12
    Abstract提出跨目标模型课程强化学习，攻破前沿模型冷启动瓶颈并实现跨模型迁移。

    该研究针对强化学习自动化提示注入红队在攻击前沿大模型时的冷启动问题，提出了一种基于目标模型鲁棒性递进的课程强化学习方法。

    Paper analysisRead analysis
You have reached the end