Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Attack technique

Defense-targeted1

Impact

Unauthorized actions9Data and privacy leaks3Output manipulation5Availability and reliability0Increased misuse capability1

Layer

Application layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack technique：Defense-targetedImpact：Availability and reliabilityImpact：Increased misuse capabilityLayer：Application layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.15383

    微软团队提出 capability laundering 攻击：弱模型拆分任务向对齐前沿模型套取能力

    提出能力洗钱攻击，拆分任务向对齐模型套取能力

    arXiv
    2609.15383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Grok-4.3 and others7

    Abstract作者提出了能力洗钱攻击，发现未对齐编排器分解咨询对齐模型可恢复能力差距，指出需建立跨会话防御。

    Paper analysisRead analysis
You have reached the end