paper-with-me

Papers

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

2026-06-19 · Jiaming He, Jiashu Zhang, Guanyu Hou, Shuhan Ye, Hanwei Zhu, Yi Yu, Xudong Jiang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.21146

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations

2025-03-26 · CVPR 2025 1 · Haitong Liu, Kuofeng Gao, Yang Bai, Jinmin Li 외

Recently, video-based large language models (video-based LLMs) have achieved impressive performance across various video comprehension tasks. However, this rapid advancement raises significant privacy and security concer…

DescriptiveText-to-Video GenerationVideo Generation

VideoGuard: Protecting Video Content from Unauthorized Editing

2025-08-05 · Junjie Cao, Kaizhou Li, Xinchun Yu, Hongxiang Li 외 arxiv

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misu…

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs

2024-07-02 · Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang 외

The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, e…

Video Understanding

Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions

2022-12-31 · Pratik K. Mishra, Alex Mihailidis, Shehroz S. Khan

The existing methods for video anomaly detection mostly utilize videos containing identifiable facial and appearance-based features. The use of videos with identifiable faces raises privacy concerns, especially when used…

Anomaly DetectionVideo Anomaly Detection

ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation

2025-10-14 · Ziyuan Luo, Yangyi Zhao, Ka Chun Cheung, Simon See 외 arxiv

The widespread adoption of Retrieval-Augmented Image Generation (RAIG) has raised significant concerns about the unauthorized use of private image datasets. While these systems have shown remarkable capabilities in enhan…

Image Generation