Score: 3

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

Published: October 14, 2025 | arXiv ID: 2510.12119v1

By: Ziyuan Luo , Yangyi Zhao , Ka Chun Cheung and more

BigTech Affiliations: NVIDIA

Potential Business Impact:

Stops AI from stealing your private pictures.

Business Areas:
Image Recognition Data and Analytics, Software

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 enhancing generation quality through reference images, protecting visual datasets from unauthorized use in such systems remains a challenging problem. Traditional digital watermarking approaches face limitations in RAIG systems, as the complex feature extraction and recombination processes fail to preserve watermark signals during generation. To address these challenges, we propose ImageSentinel, a novel framework for protecting visual datasets in RAIG. Our framework synthesizes sentinel images that maintain visual consistency with the original dataset. These sentinels enable protection verification through randomly generated character sequences that serve as retrieval keys. To ensure seamless integration, we leverage vision-language models to generate the sentinel images. Experimental results demonstrate that ImageSentinel effectively detects unauthorized dataset usage while preserving generation quality for authorized applications. Code is available at https://github.com/luo-ziyuan/ImageSentinel.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡­πŸ‡° United States, Hong Kong

Repos / Data Links

Page Count
24 pages

Category
Computer Science:
CV and Pattern Recognition