Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack type

Jailbreaks1Prompt injection12Poisoning and backdoors6Detection evasion8

Defense type

Detection and filtering1

System type

Models and APIs17LLM applications1AI Agent6coding agent0Browser and computer use0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksDefense type：Detection and filteringSystem type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2601.19051

    Proactively hardening LLM defenses with HASTE

    提出 HASTE，挖掘 hard negative 再训练恶意提示检测器

    arXiv
    2601.19051
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Evaluated models
    protectai/deberta-v3-base-prompt-injection
    AbstractHASTE 用 hard negative 再训练检测器。

    HASTE 是检测器侧的闭环硬化框架：持续构造能绕过当前检测的对抗提示，再用来更新恶意提示分类器。

    Paper analysisRead analysis
You have reached the end