Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter1

Defense type

Detection and filtering3

Impact

Output manipulation5

System type

Models and APIs7

Attack surface / entry point

Images, audio and video3

Layer

Model layer5

System component

MCP and skills15Memory27RAG8Guardrails and judges64Monitors27Reasoning chains10Permissions and sandboxing12Fine-tuning and open weights5Vision30Audio11Video8Image generation7Multimodal49
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 313papers have no tags yet and are not included in filtered results.
System component：VideoClear all

Another 313papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. Evaluation and benchmarksarXiv 2610.06339

    BabelFake：面向多语言音视频 DeepFake 检测的基准数据集

    构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器

    arXiv
    2610.06339
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    SpeechForensics, AVH-Align, (B)RAVEn
    AbstractBabelFake 为五语同意采集基准。

    BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准，用来把视觉操纵和语音合成拆开比较。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2608.18607

    VA-Judger：面向联合视频-音频生成的人类偏好反馈奖励建模

    提出 VA-Judger，用人类偏好训练联合音视频奖励模型

    arXiv
    2608.18607
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    VA-Judger, LTX-2 + VA-Judger
    AbstractVA-Judger 用易到难的人类偏好学习做联合音视频奖励，并用于 LTX-2 后训练。

    VA-Judger 是面向联合音视频生成的思维链全模态奖励模型，用来替代由分维度专家指标拼成的强化学习奖励。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2605.18984

    Artifact-Bench：评估 MLLM 检测与诊断 AI 生成视频伪影

    提出 Artifact-Bench，评测 MLLM 检测并诊断 AI 生成视频伪影

    arXiv
    2605.18984
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemini 3.1 Pro, Gemini 3 Flash, Qwen3-VL 8B-Instruct and others19
    AbstractArtifact-Bench 以三项任务评 MLLM 的 AIGC 伪影感知。

    Artifact-Bench 用来看 MLLM 能否发现 AI 生成视频中的伪影，并说明视频为何不真实。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2602.10639

    VideoSTF 揭示视频大模型输出重复问题

    提出 VIDEO STF 评测视频大模型输出重复并压力测试时序扰动

    arXiv
    2602.10639
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-Video-7B-Qwen2, LLaVA-Video-7B-Qwen2-Video-Only, LLaVA-NeXT-Video-7B and others10
    AbstractVIDEO STF 把输出重复做成可测、可被时间扰动放大、并可黑盒诱导的失败。

    VIDEO STF 测量 VideoLLM 的输出重复，并把时间变换用作 black-box 诱导。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2512.03992

    DIQ-H 基准与 VGIR 框架：评估 VLM 在对抗视觉条件下的鲁棒性

    提出 DIQ-H 基准，评测 VLM 在连续退化视觉流中的幻觉残留与恢复

    arXiv
    2512.03992
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-7B-strict, InternVL2-8B-strict, Phi-3-Vision-strict and others17
    AbstractDIQ-H 用连续退化视频测幻觉延续与恢复，VIR 用不确定性过滤生成伪标注。

    DIQ-H 评测 VLM 在连续视觉退化中的幻觉、恢复和跨时间一致性。VIR 用轻量模型的不确定性过滤生成伪真值。

    Paper analysisRead analysis
You have reached the end