Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter4

Defense type

Model hardening3Inference-time intervention3Detection and filtering14Instruction–data separation11Permissions and approval21Monitoring and auditing19

System type

Models and APIs121LLM applications3AI Agent23coding agent1Browser and computer use1Multi-agent systems1Embodied systems and robotics7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Defense type：Model hardeningSystem type：coding agentSystem type：Browser and computer useSystem type：Multi-agent systemsClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.04412

    论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性

    提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位

    arXiv
    2610.04412
    Published
    Layer
    Application layer
    Setting
    LLM applications, Multi-agent systems
    Evaluated models
    LLaMA-2 7B, LLaMA-3 8B, GPT 3.5 Turbo and others14
    Abstract三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。

    这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.00850

    AuraForge：为训练安全编码 Agent 扩展安全监督

    提出 AuraForge，从漏洞修复合成安全测试并训练编码 Agent

    arXiv
    2610.00850
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen3.5-4B, GLM 4.7 Flash, Qwen3-Coder-Next and others7
    AbstractAuraForge 用攻击效果测试和防泄露环境做成 AuraGym，合成监督的误拒更低，训出的 4B 模型增益高于人工测试。

    AuraForge 把真实仓库的历史漏洞修复变成可执行训练任务，用来监督编程智能体同时满足功能请求和隐含的安全要求。

    Paper analysisRead analysis
You have reached the end