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

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.

Key Contributions

• Formalizes the novel threat of unauthorized visual dataset use in retrieval-augmented image generation (RAIG) systems, where traditional watermarking fails due to feature recombination destroying embedded signals
• Proposes ImageSentinel, which synthesizes visually consistent sentinel images using VLMs and embeds random character sequence retrieval keys to enable reliable detection of unauthorized dataset use
• Demonstrates that the framework detects unauthorized usage without degrading generation quality for authorized applications

🛡️ Threat Analysis

Details

Similar Papers