Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Defense type

Model hardening11Inference-time intervention3Detection and filtering14Instruction–data separation1Permissions and approval0

System type

Models and APIs1AI Agent11
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：Instruction–data separationDefense type：Permissions and approvalSystem type：Models and APIsClear all

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

  1. Evaluation and benchmarksarXiv 2602.04294

    少样本示例如何影响针对 LLM 越狱攻击的提示词防御

    分析少样本示范对 RoP 与 ToP 提示防御抗越狱效果的影响

    arXiv
    2602.04294
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Pangu-Embedded-1B, Pangu-Embedded-7B, Pangu-Embedded-7B-Think and others9
    Abstractfew-shot 可抬高 RoP、压低 ToP，但表内有反号，Think 模型更低。

    作者评估 few-shot 示范如何改变 RoP 与 ToP 对越狱的防御效果。

    Paper analysisRead analysis
You have reached the end