ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization

2026-06-19

AI Summary

This work proposes ChronoLock, the first proactive defense framework designed to safeguard online videos against misuse in fine-tuning text-to-video (T2V) personalization models by disrupting the modeling of temporal dynamics. ChronoLock achieves this by optimizing bounded perturbations along the denoising trajectory of diffusion models, simultaneously degrading intra-clip temporal coherence and inter-clip motion continuity, thereby impeding T2V models’ ability to learn authentic motion patterns. Experimental results on the UCF Sports and HMDB51 datasets demonstrate that ChronoLock significantly undermines the motion imitation capabilities of state-of-the-art T2V models. The effectiveness and practicality of the approach are rigorously validated through both automated metrics and human evaluation.

Abstract

Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such models to imitate a specific subject, style, or motion pattern from only a few reference clips. This capability creates a new data-misuse risk: videos shared online can be collected and used for unauthorized T2V fine-tuning. Existing protective perturbations are mainly designed for image recognition or text-to-image personalization, and therefore focus on corrupting static appearance cues rather than the temporal denoising dynamics that make video personalization possible. To address this gap, we introduce ChronoLock, the first proactive protection framework that makes released videos difficult to exploit for unauthorized T2V personalization. ChronoLock targets the motion-learning process directly by optimizing bounded perturbations over temporal denoising trajectories. It first disrupts intra-chunk temporal adaptation with a diffusion objective that combines fitting error, frame-relative denoising relations, and adjacent-frame variation, and then enlarges inter-chunk boundary mismatch to weaken long-range motion continuity. Transformation-sampled updates further improve robustness to common preprocessing operations.Experiments on UCF Sports and HMDB51 with popular T2V backbones and personalization scheme show that ChronoLock effectively reduces motion imitation under automatic metrics and human evaluation.

Problem

• text-to-video personalization
• unauthorized fine-tuning
• video protection
• temporal denoising dynamics
• data misuse

Innovation

• text-to-video personalization
• temporal denoising dynamics
• motion imitation protection
• bounded perturbations
• ChronoLock