Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

System type

Models and APIs55LLM applications2AI Agent4coding agent0Browser and computer use0

Attacker access

Black-box23Gray-box4White-box2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
System type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useAttacker access：White-boxClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.05870

    MBZUAI 提出可校准的真实图像认证方法

    提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动

    arXiv
    2610.05870
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    White-box

    Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.08394

    Windows 恶意软件检测器作为复合 AI 系统：准确率、效率与对抗鲁棒性的权衡

    提出 OBELISK 三级流水线，权衡恶意软件检测的准确率、开销与鲁棒性

    arXiv
    2609.08394
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    White-box, Black-box
    Evaluated models
    GBDT-ALL, GBDT-YARA, NEBULA-ALL and others4
    Abstract三级过滤以不大的检测损失换速度，同一机制扩大攻击面，部署应按约束选配置。

    OBELISK 把 Windows PE 恶意软件检测做成 YARA、EMBER-GBDT 与 Nebula 的顺序流水线，用来同时看检出、计算开销和对抗鲁棒性。

    Paper analysisRead analysis
You have reached the end