Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter1

Attack type

Jailbreaks3

Impact

Harmful content4Output manipulation3

System type

Models and APIs7

Attacker access

Black-box3

Attack surface / entry point

User input4Images, audio and video3

Layer

Prompt layer4Model layer3

System component

MCP and skills15Memory27RAG8Guardrails and judges64Monitors27Reasoning chains10Permissions and sandboxing12Fine-tuning and open weights5Vision32Audio11Video8Image generation7Multimodal51
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.
System component：Image generationClear all

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

  1. Evaluation and benchmarksarXiv 2610.11112

    EpiReal-Bench：商用图像生成模型虚假声明红队基准

    构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据

    arXiv
    2610.11112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
    Abstract四款商用图像模型能把假主张画成可信证据。

    EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2610.07939

    CCDF 数据集：Grok Imagine、Veo 3.1、Sora 2 伪造监控录像，十个深伪检测器基本认不出

    提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别

    arXiv
    2610.07939
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    C2P-CLIP, ForgeLens, D3-Im and others10

    Abstract提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.07216

    DIVA：利用视觉锚点对视频生成模型实施多模态越狱

    提出 DIVA，将有害意图拆成视觉锚点与运动文本以越狱视频生成模型

    arXiv
    2609.07216
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Wan, CogVideoX, LTX-Video and others9
    AbstractDIVA 用视觉锚点抑制语义漂移做视频越狱，并给出多条件安全基准 TI2VSafetyBench。

    DIVA 是针对带参考图的视频生成模型的免训练 black-box 越狱：用一致性机制本身堵住语义漂移这条安全逃逸路径。。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2609.06991

    AV-SafetyBench：面向文本到音视频生成的安全基准

    提出 AV-SafetyBench 评测文生音视频模型的不安全生成

    arXiv
    2609.06991
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LTX-2.3, Ovi-1.1, JavisDiT++ and others7
    AbstractAV-SafetyBench 用三视角评五个 T2AV 模型，显示只看视频会漏掉音频与联合风险。

    AV-SafetyBench 是面向文本生成音视频（T2AV）的安全基准：一条提示词同时规定画面和音频，评测同时看两轨以及它们的交互。作者要测的是，不安全含义不只出现在画面上：它可以主要由语音或声音承载，也可以只有两轨合起来才成立。T2VSafetyBench 不评音频，TTA-Bench 不评与画面的交互，作者认为二者都盖不住这些路径。

    Paper analysisRead analysis
You have reached the end