Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter2

Defense type

Model hardening5Inference-time intervention6Detection and filtering14Watermarking and provenance4

Impact

Output manipulation3

System type

Models and APIs5

Attacker access

White-box3

Attack surface / entry point

User input32Web pages and interfaces6Documents and messages3Tool responses6Images, audio and video5Training data21Weights and gradients12

Layer

Training and data layer3

System component

Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Defense type：Model hardeningAttack surface / entry point：Images, audio and videoClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.33481

    IDUnlearn-Bench：面向视觉语言模型的个体级遗忘基准

    提出 IDUnlearn-Bench，评测 VLM 个体级遗忘后的身份残留

    arXiv
    2609.33481
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others6
    AbstractIDUnlearn-Bench 用四族探针显示：压低直接属性访问后，身份仍常能被反向查出、绑定或重构。

    IDUnlearn-Bench 评测 VLM 是否忘掉一个可跨模态识别的人，而不只是答不出某条监督事实。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.23596

    StyleAT：用对抗训练防御人脸识别的语义攻击

    提出 BoundStyle 与 StyleAT，对抗训练防御人脸识别语义攻击

    arXiv
    2609.23596
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    MobileFaceNet (MobileFace), ResNet (ResNet-152, IR-SE), RepVGG and others7
    AbstractBoundStyle 用 StyleGAN3 有界潜编辑快速攻击 FR。

    StyleAT 用可调的 StyleGAN3 潜空间攻击 BoundStyle 对人脸识别做对抗训练，以抵抗一般语义编辑，并在评测中面对训练时未见的 DiffPrivate。

    Paper analysisRead analysis
  5. DefensesarXiv 2602.12461

    面向 CLIP 的语义感知对抗微调

    提出 SAFT，用语义描述集成构造对抗样本并微调图像编码器

    arXiv
    2602.12461
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ViT-B/32, CLIP-L/14
    AbstractSAFT 用精炼类描述的集成对抗样本微调 CLIP 图像编码器，以改善零样本准确率与鲁棒性的权衡。

    SAFT 是对 CLIP 图像编码器做对抗微调的方法，要改善零样本分类上的准确率–鲁棒性权衡。

    Paper analysisRead analysis
You have reached the end