RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (42) · 35784-35792
DOI: 10.1609/aaai.v40i42.40892 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yehan Sun und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Diffusion models have gained widespread adoption due to their ability to generate highly realistic images, yet their rapid proliferation also raises security and traceability concerns. To address issues of ownership verification and accountability, current watermarking techniques primarily focus on embedding information into the internal mechanisms of generative pipelines. Nevertheless, many existing methods inject watermarks directly into latent representations without adequately exploiting inherent redundancies or perceptual properties in latent space, leading to degraded image quality. In this work, we conduct a systematic analysis aimed at quantifying differentiated redundancies present within latent space, and further propose a novel Redundancy-Aware Latent Injection framework RAIN based on the above analysis. Specifically, a redundancy‑aware adaptive watermark fusion method is introduced to preserve image quality, which utilizes the differentiated redundancy distribution to guide adaptive watermark allocation in different perception tolerance regions. Moreover, a distribution alignment initialization strategy is designed to align the watermark’s initial distribution to the latent prior, reducing initialization bias and improving convergence efficiency. Comprehensive experimental evaluations demonstrate that RAIN achieves state-of-the-art performance by delivering superior perceptual quality under high-capacity watermarking scenarios.
Zitieren
APA
Sun, Y., Ni, R., Tan, C., Liu, H., Ni, W., Tao, R., & Zhao, Y. (2026). RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking. Proceedings of the AAAI Conference on Artificial Intelligence, 40(42), 35784-35792. https://doi.org/10.1609/aaai.v40i42.40892
Vancouver
Sun Y, Ni R, Tan C, Liu H, Ni W, Tao R, et al. RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(42):35784-35792. doi:10.1609/aaai.v40i42.40892
BibTeX
@article{Sun2026,
author = {Sun, Yehan and Ni, Rongrong and Tan, Chuangchuang and Liu, Huan and Ni, Wenhao and Tao, Renshuai and Zhao, Yao},
title = {RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {42},
pages = {35784--35792},
doi = {10.1609/aaai.v40i42.40892}
}
EUVIMED