Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter4

Attack technique

Conversation structure manipulation0Defense-targeted1

Layer

Training and data layer1

System component

Guardrails and judges3Monitors1Fine-tuning and open weights8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack technique：Conversation structure manipulationAttack technique：Defense-targetedLayer：Training and data layerSystem component：MonitorsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2601.14310

    CORVUS：用 LoRA 伪装内部信号绕过单次幻觉检测器

    提出 CORVUS，用 LoRA 伪装内部遥测以绕过幻觉检测器

    arXiv
    2601.14310
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Vicuna-7B (v1.5), Llama-3-8B-Instruct and others4

    Abstract作者称内部遥测在自适应模型侧对抗下易被操纵，CORVUS 通过轻量适配器微调降低了多种幻觉检测器的效果。

    Paper analysisRead analysis
You have reached the end