发表机构
GIST; POSTECH（光州科学技术院; 浦项科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Anti-Prompt方法，通过向图像注入不可察觉的扰动，在文本引导的图像到视频生成中引发视觉不一致和结构失败，从而保护版权和隐私。
AI 中文摘要
近期图像到视频生成的进展使得单张图像能够在文本引导下动画化为令人信服的视频，这引发了严重的版权和隐私风险。我们提出Anti-Prompt，一种图像保护方法，通过向图像注入不可察觉的扰动，在文本引导的I2V生成中引发可见的不一致性和结构失败。我们的方法源于一个简单的经验观察：当从现代I2V模型中移除文本引导时，生成质量显著下降，不仅在运动真实性方面，而且在主体保持、结构连贯性和时间一致性方面。基于这一见解，Anti-Prompt利用模型对文本引导的依赖，通过减弱去噪过程中文本条件交互，同时增强仅视觉路径。为了进一步系统评估保护效果，我们引入了一个视频LLM辅助的评估协议，该协议提供可解释的、基于帧的生成伪影和不一致性分析。在两个代表性I2V架构上的实验表明，我们的方法在提高效率和跨模型可迁移性的同时，实现了强大的保护性能。
英文摘要
Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image, inducing visible inconsistencies and structural failures in text-guided I2V generation. Our method is motivated by a simple empirical observation. When text guidance is removed from modern I2V models, generation quality degrades markedly, not only in motion realism but also in subject preservation, structural coherence, and temporal consistency. Building on this insight, Anti-Prompt exploits the model reliance on textual guidance by attenuating text-conditioned interactions during denoising while strengthening visual-only pathways. To further systematically evaluate protection effectiveness, we introduce a Video-LLM-assisted evaluation protocol that provides interpretable, frame-grounded analyses of generation artifacts and inconsistencies. Experiments on two representative I2V architectures demonstrate that our method achieves strong protection performance while improving efficiency and cross-model transferability.
CommentsAccepted to ECCV 2026
