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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Luo, Ziyuan, Zhao, Yangyi, Cheung, Ka Chun, See, Simon, Wan, Renjie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908591631368192
author Luo, Ziyuan
Zhao, Yangyi
Cheung, Ka Chun
See, Simon
Wan, Renjie
author_facet Luo, Ziyuan
Zhao, Yangyi
Cheung, Ka Chun
See, Simon
Wan, Renjie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
Luo, Ziyuan
Zhao, Yangyi
Cheung, Ka Chun
See, Simon
Wan, Renjie
Computer Vision and Pattern Recognition
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.
title ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12119