Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization

2026-07-14

AI Summary

Existing video identity protection methods struggle to defend against reference-based (e.g., image-to-video) and fine-tuning-based customized attacks, and exhibit limitations in temporal compression, cross-video generalization, and temporal consistency. This work proposes Temporally Consistent Universal Adversarial Perturbations (TC-UAP), a novel approach that optimizes identity-level multi-frame perturbations via a multi-video sliding window framework, thereby unifying defense against both attack types for the first time. TC-UAP integrates temporal compression modeling through a video VAE, multi-frame UAP optimization, sliding-window training, and a temporally aware adversarial proxy loss to ensure both temporal consistency and robustness of the generated perturbations. Experiments demonstrate that TC-UAP achieves state-of-the-art identity protection under both reference-based and fine-tuning-based attack scenarios and maintains strong robustness against various unseen temporal attacks.

Abstract

Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which fine-tune a video diffusion model, and reference-based pipelines such as image-to-video generation. However, these capabilities raise serious concerns about personal privacy, identity ownership and intellectual property protection. Existing anti-customization works focus on protecting images, while protection for videos against both reference- and tuning-based customization remains largely underexplored. Protecting videos in this setting raises three challenges: (i) Image-level perturbations, optimized frame by frame, cannot survive temporal compression by 3D video VAE. (ii) A video-level perturbation optimized on a single video is vulnerable to temporal editing and fails to protect unseen videos. (iii) Temporally inconsistent perturbations are not robust to temporal attacks. To address these challenges, we propose Temporally Consistent Universal Adversarial Perturbations (TC-UAP), the first protection method against both reference- and tuning-based video customization. TC-UAP optimizes an identity-level multi-frame UAP over sliding windows from multiple videos, accounting for local temporal dependencies induced by temporal compression in video VAE and enabling a single perturbation to protect unseen videos of varying lengths. Moreover, we introduce intrinsic temporal modeling and an extrinsic surrogate temporal-attack loss, which make the perturbation temporally consistent and robust to unseen temporal attacks. Empirically, quantitative and qualitative results show that TC-UAP achieves the strongest identity protection compared with existing methods under both reference- and tuning-based video customization, and remains robust under multiple unseen temporal attacks.

Problem

• video protection
• anti-customization
• temporal robustness
• identity ownership
• diffusion models

Innovation

• Temporal Consistency
• Universal Adversarial Perturbation
• Video Protection
• Diffusion Models
• Identity Preservation