Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack type

Jailbreaks4Prompt injection9Poisoning and backdoors5Detection evasion5Malicious use3

Defense type

Inference-time intervention4Detection and filtering3Permissions and approval0Monitoring and auditing4

System component

Monitors0Embeddings0Multimodal3
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 type：Malicious useDefense type：Detection and filteringDefense type：Permissions and approvalSystem component：MonitorsSystem component：EmbeddingsSystem component：MultimodalClear all

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

  2. DefensesarXiv 2608.00716

    生成图像更易被遗忘：面向合成图像检测的机器遗忘视角

    提出机器遗忘式生成图像检测，用遗忘前后特征相似度区分自然图与生成图

    arXiv
    2608.00716
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    DINOv2 ViT-S/14, DINOv2 ViT-B/14, DINOv2 ViT-L/14 and others9
    Abstract作者用剪枝或 LoRA 遗忘拉开生成图与自然图的特征相似度，并在多个检测基准上报告结果。

    这篇工作把 AI 生成图像检测写成对预训练视觉模型的机器遗忘：原模型对两类图像损失都低，剪枝后生成图特征变得更不像原模型。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.01544

    RA-Det：利用鲁棒性不对称检测 AI 生成图像

    提出 RA-Det，利用鲁棒性不对称检测 AI 生成图像

    arXiv
    2603.01544
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractRA-Det 把扰动下特征漂移差变成检测信号，平均 ACC 高于表中通用检测器，但不是每行最高。

    RA-Det 是合成图像检测器，用扰动下的表示稳定性差异代替外观痕迹。

    Paper analysisRead analysis
You have reached the end