通过时间冻结技术防止恶意图像生成视频，保护图像不被滥用。
Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
- 在图像中添加不可察觉扰动，使生成视频静止不动
- 实验显示对多种模型均有强防护效果，有效阻断恶意视频生成
- 适合关注AI安全与内容防护的研究者和开发者
图像到视频（I2V）生成模型的快速发展带来了显著风险，可利用单张图像生成欺骗性或恶意视频。现有防御如I2VGuard通过引入时空退化来免疫图像，但残余运动仍可能传达恶意意图。本文提出Vid-Freeze——一种新型对抗性防御方法，通过添加不可察觉扰动，强制生成视频进入时间冻结状态。该方法直接针对I2V模型中的注意力动态，抑制运动合成。结果表明，经免疫的图像生成的视频为静止或近似静态，有效阻止恶意内容生成。实验验证了其在多种模型上的强保护能力，支持时间冻结作为主动且有意义的I2V滥用防御方向。
原文摘要 · Abstract (English)
The rapid progress of image-to-video (I2V) generation models has introduced significant risks by enabling deceptive or malicious video synthesis from a single image. Prior defenses such as I2VGuard attempt to immunize images by inducing spatio-temporal degradation, which does not necessarily provide meaningful protection, since residual motion can still convey malicious intent. In this work, we introduce Vid-Freeze -- a novel adversarial defense that adds imperceptible perturbations to enforce temporal freezing in generated videos. Our method explicitly targets attention dynamics in I2V models to suppress motion synthesis. As a result, immunized images produce standstill or near-static videos, effectively blocking malicious content generation. Experiments demonstrate strong protection across models and support temporal freezing as a promising direction for proactive and meaningful defense against I2V misuse.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。