Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Defense type

Model hardening15Inference-time intervention3Detection and filtering4Permissions and approval3Watermarking and provenance0

Impact

Harmful content20Unauthorized actions6Data and privacy leaks6Output manipulation20Availability and reliability3

System type

Models and APIs3

Layer

Model layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Defense type：Inference-time interventionDefense type：Watermarking and provenanceImpact：Availability and reliabilityClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.01170

    HeadEdit：通过冻结的 unembedding 矩阵校准语言模型行为

    提出 HeadEdit，经冻结 unembedding 做随输入变化的 logit 校正

    arXiv
    2610.01170
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Gemma-3-4B-IT, Llama-3.2-3B-Instruct and others4
    Abstract低秩 unembedding 校正抬高九个设置的总体准确率，并可部分预测 DPO 更新。

    HeadEdit 是一种不更新参数的行为校准方法，作用点是冻结的 unembedding，而不是中间层残差或新的梯度优化。

    Paper analysisRead analysis
You have reached the end