Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

Impact

Harmful content3

System component

Guardrails and judges17Monitors3Fine-tuning and open weights3Vision4Audio3Image generation4Multimodal10
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.
Impact：Harmful contentSystem component：Fine-tuning and open weightsClear all

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

  1. Evaluation and benchmarksarXiv 2608.08542

    SkillSafe-Bench：技能合并模型静态安全无法预测自适应越狱鲁棒性

    提出 SkillSafe-Bench，评测技能合并模型的自适应越狱鲁棒性

    arXiv
    2608.08542
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others6
    Abstract论文报告了技能合并大模型在静态安全与自适应越狱间的脱节，提出了评测基准与无数据子空间投影修复方法。

    本研究针对开源语言模型技能合并过程中的安全评估盲区，系统评测并刻画了合并大模型在自适应越狱攻击下的脆弱性特征。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2605.14605

    研究：恶意微调防御在持续训练下失效，72 条防御轨迹危害度全部上升

    用代价曲线评估恶意微调防御在持续训练下的衰减

    arXiv
    2605.14605
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat, Qwen3-8B, Llama-3.1-8B-Instruct and others8

    Abstract论文指出恶意微调防御在持续训练下均会衰减，表明基于有限攻击者假设的防御无法为开源模型提供持久保护。

    Paper analysisRead analysis
You have reached the end