Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5

Attack type

Jailbreaks15Extraction and theft3Malicious use4

Impact

Harmful content4Data and privacy leaks3

System type

Models and APIs6

Attack surface / entry point

User input7Retrieval corpus3Images, audio and video5

Layer

Model layer4

System component

MCP and skills3RAG6Guardrails and judges3Monitors6Reasoning chains5Fine-tuning and open weights3Vision3Image generation6Embeddings1Multimodal11
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack type：Malicious useAttack surface / entry point：User inputSystem component：Image generationSystem component：EmbeddingsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. 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

    arXiv
    2610.03980
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    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
  4. 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

    arXiv
    2609.03629
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    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
  5. 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

    arXiv
    2607.01276
    Published
    Layer
    Application layer
    Setting
    LLM applications
    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
You have reached the end