Skip to content

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

Oct 12 · Monday

All papers

Found 17 papers

Another 261papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.13733

    KVeil: First-Place Solution for the ECCV 2026 LifeGenIP Unlearnable Video Challenge

    Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity

    Published
    Evaluated models
    Wan2.2-TI2V-5B, HunyuanVideo-1.5, Kling 3.0 and others4

    AbstractKVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.13333

    LETHE: Defending Against Unauthorized Image-to-Video Generation via Value Diversity Collapse

    Proposes LETHE, which perturbs reference images to block unauthorized image-to-video

    Published
    Evaluated models
    Wan2.1-I2V-14B, CogVideoX-5B-I2V, LightX2V and others6
    AbstractLETHE suppresses the diversity of reference values and attracts attention, making protected images difficult to animate faithfully.

    LETHE is a protective perturbation added to personal images before publication, used to counter unauthorized image-to-video generation.

    Paper analysisRead analysis
  3. AttacksarXiv 2610.05601

    Tracer 框架可从遗忘后的扩散模型中识别被擦除概念

    提出 TRACER,从权重差识别扩散模型被擦除概念

    Published
    Attacker
    White-box
    Evaluated models
    Stable Diffusion v1.5, Stable Diffusion 3, FLUX.1 and others5
    AbstractTRACER 用权重足迹识别未披露擦除概念并估计个数,作者称数秒内完成且准确率高于对照。

    TRACER 针对的是遗忘扩散模型上的目标识别:提供者从公开基座 W 用已发表方法擦掉未知集合 S⋆,只发布 W′。攻击者还有假定包含这些概念的词表,但不知擦了谁、擦了几个、用了什么算法。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.03980

    FADE:面向视频扩散模型的帧感知多概念擦除框架

    提出 FADE,对文生视频模型做帧感知多概念擦除

    Published
    Evaluated models
    Wan2.1-T2V-1.3B, Wan2.1-T2V-14B, CogVideoX-2B and others4
    AbstractFADE 用闭式编辑、帧感知适配器和软路由,在单骨干上擦除多概念并压低逐帧残差。

    FADE 是面向文生视频扩散 Transformer 的多概念遗忘方法,用来抑制指定物体、画风、裸体、暴力、仇恨和名人身份,并尽量保持其他生成。作者要处理两件事。与帧无关的抑制会让概念在少数帧重现,片段均值会掩盖这一失败。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.23586

    VidMark:面向视频生成模型知识产权保护的高效水印方案

    提出 VidMark 水印方案,核验视频生成模型的输出来源与所有权

    Published
    Evaluated models
    Stable Video Diffusion (SVD), Open-Sora, Wan
    AbstractVidMark 加解码器引导微调,把模型签名写入 VGM 输出并用于两项核验。

    Huang 等人提出一套面向视频生成模型的生成内嵌水印方案,用来同时判断一条视频是否来自受保护模型,以及一个嫌疑模型是否为该模型的拷贝。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.04767

    SHAQ: Privacy-preserving retrieval in vector databases using shadow queries

    Proposes SHAQ, which replaces document embeddings with shadow query embeddings to defend against embedding inversion.

    Published
    Attacker
    Black-box
    Evaluated models
    GTR-T5 encoder, DPR
    AbstractSHAQ replaces document embeddings with shadow query embeddings.

    SHAQ is a defense against EIA for cloud vector databases: instead of directly modifying document embeddings, it replaces them with shadow query embeddings.

    Paper analysisRead analysis
  7. DefensesarXiv 2609.03629

    EraseSAE:用稀疏自编码器在文生视频扩散模型中实现精准概念擦除

    提出 EraseSAE,在文生视频模型中局部擦除指定概念

    Published
    Evaluated models
    CogVideoX-5B, HunyuanVideo, Flux.1 [dev]
    AbstractEraseSAE 用单义特征局部擦除。

    EraseSAE 把 SAE 用于 DiT 文生视频模型的概念擦除。作者要解决的是:全局改权重或表面负提示对不齐细粒度、分布式的概念,而且会改到无关时空区域。

    Paper analysisRead analysis
  8. AttacksarXiv 2607.01276

    研究者提出嵌入推断攻击 EIA,可在黑盒 IR 系统中识别所用嵌入模型

    提出嵌入推断攻击 EIA,在黑盒 IR 中识别所用嵌入模型

    Published
    Attacker
    Black-box
    Evaluated models
    e5-small, e5-small-v2, e5-base and others19
    AbstractEIA 用无序文档集的差异从候选中识别嵌入模型,并给出 reranker 与阈值下的计数。

    EIA 是在黑盒 IR 上识别所用嵌入模型的攻击。。

    Paper analysisRead analysis
  9. 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

    Published
    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
  10. AttacksarXiv 2602.01757

    Zero2Text: Training-Free Cross-Domain Text Embedding Inversion Attack

    提出 Zero2Text,无需训练地跨域反演文本嵌入

    Published
    Attacker
    Black-box
    Evaluated models
    GTR-Base, Qwen3-Embedding-0.6B, Text-Embedding-3-small and others4
    Abstract零训练在线对齐可在未知域、无泄漏对时从黑盒 embedding 还原句子。

    Zero2Text 是一种不训练 decoder、也不使用泄漏文本–向量对的文本 embedding 反演,针对 RAG 向量库在严格黑盒、目标域未知时的还原。

    Paper analysisRead analysis
  11. AttacksarXiv 2508.06837

    Prometheus:针对文生图扩散模型的免训练提示词窃取攻击

    提出 Prometheus,从展示图反推文生图模型的在售提示词

    Published
    Evaluated models
    Midjourney, Leonardo.ai, DALL·E and others4
    Abstract训练无关的 proxy 搜索攻击。

    Prometheus 是针对文生图市场 showcase 的训练无关提示词窃取:攻击者看不到在售文本,只用本地开源 proxy 恢复 subject 和 modifier,并希望换 subject 后风格仍在。

    Paper analysisRead analysis
You have reached the end