Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

Defense type

Model hardening3

System type

Models and APIs3

Attack surface / entry point

User input4Training data3

Layer

Training and data 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：Model hardeningAttack surface / entry point：Training dataClear all

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

  3. 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