arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.24570cs.CVcs.AI
收藏

Anti-I2V: 保护您的照片免受恶意图像到视频生成的威胁

Anti-I2V: Safeguarding your photos from malicious image-to-video generation

Qualcomm AI Research(高通人工智能研究)

Duc Vu, Anh Nguyen, Chi Tran, Anh Tran

AI总结:

针对图像到视频扩散模型的恶意生成问题,Anti-I2V在L*a*b*和频域中操作,提升鲁棒性并聚焦显著像素,通过优化训练目标提升时间一致性与生成保真度,展现先进防御性能。

摘要:

扩散基视频生成模型的进展虽显著提升了人类动画质量,但通过特定人物照片和文本提示生成虚假视频存在滥用风险。近期研究聚焦于对抗攻击,通过引入精心设计的扰动保护图像免受扩散模型的侵害。然而,现有方法大多针对图像生成,较少直接针对图像到视频扩散模型(VDMs),且多数基于UNet架构。因此,其对扩散Transformer(DiT)模型的有效性仍待探索,因这些模型因更大容量和先进注意力机制而表现出更强的特征保留和时间一致性。本文提出Anti-I2V,一种新型防御机制,适用于多种扩散后端。不同于限制噪声更新至RGB空间,Anti-I2V在L*a*b*和频域中操作,提升鲁棒性并聚焦显著像素。随后,识别在去噪过程中捕捉最多不同语义特征的网络层,设计合适的训练目标以最大化时间一致性与生成保真度的降级。通过广泛验证,Anti-I2V在多种视频扩散模型上展现最先进的防御性能,提供有效解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑