Anti-I2V：保护你的照片免受恶意图像到视频生成侵害
Anti-I2V: Safeguarding your Photos from Malicious Image-to-video Generation
针对 DiT 架构的视频扩散模型提出跨骨干的对抗扰动防御，在 L*a*b* 与频域联合优化噪声，并定位去噪过程中语义特征最强的网络层来设计训练目标，可直接迁移到图像/视频生成模型的版权保护与防滥用攻击设计。
原文依据 Anti-I2V operates in both the L*a*b* and frequency domains, improving robustness and concentrating on salient pixels.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散的视频生成模型的进展在显著提升人体动画效果的同时，也带来了滥用风险，即利用特定人物的照片和文本提示生成虚假视频。近期研究主要集中于通过引入精心构造的扰动来保护图像免受扩散模型侵害的对抗攻击。然而，现有方法大多针对图像生成，明确面向图像到视频扩散模型（VDM）的工作相对较少，且多数主要关注基于 UNet 的架构。因此，这些方法针对扩散 Transformer（DiT）模型的有效性在很大程度上仍未被充分探索，因为此类模型凭借更大的容量和更先进的注意力机制，展现出更强的特征保留能力和更强的时序一致性。在本工作中，我们提出 Anti-I2V，一种针对恶意人体图像到视频生成的新型防御方法，可适用于多种扩散骨干网络。Anti-I2V 不将噪声更新限制在 RGB 空间，而是同时在 L*a*b* 域和频域中操作，从而提升鲁棒性并聚焦于显著像素。随后，我们识别出去噪过程中捕获最独特语义特征的网络层，据此设计合适的训练目标，以最大程度地破坏时序一致性和生成保真度。通过大量验证，Anti-I2V 在面对多种视频扩散模型时展现出最优的防御性能，为该问题提供了有效的解决方案。
英文原文摘要 1515 字符
Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on adversarial attacks that introduce crafted perturbations to protect images from diffusion-based models. However, most existing approaches target image generation, while relatively few explicitly address image-to-video diffusion models (VDMs), and most primarily focus on UNet-based architectures. Hence, their effectiveness against Diffusion Transformer (DiT) models remains largely under-explored, as these models demonstrate improved feature retention, and stronger temporal consistency due to larger capacity and advanced attention mechanisms. In this work, we introduce Anti-I2V, a novel defense against malicious human image-to-video generation, applicable across diverse diffusion backbones. Instead of restricting noise updates to the RGB space, Anti-I2V operates in both the L*a*b* and frequency domains, improving robustness and concentrating on salient pixels. We then identify the network layers that capture the most distinct semantic features during the denoising process to design appropriate training objectives that maximize degradation of temporal coherence and generation fidelity. Through extensive validation, Anti-I2V demonstrates state-of-the-art defense performance against diverse video diffusion models, offering an effective solution to the problem.