Invisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection
ACM Transactions on Multimedia Computing, Communications, and Applications · 28.02.2025 · 21 (2) · 1-22
DOI: 10.1145/3652608 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 24.12.2024. Verfasst von Jinwei Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhongyuan Science and Technology Innovation Leading Talent Project of China, Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness.
Abstract (Originalsprache)
Invisible watermarking can be used as an important tool for copyright certification in the Metaverse. However, with the advent of deep learning, Deep Neural Networks (DNNs) have posed new threats to this technique. For example, artificially trained DNNs can perform unauthorized content analysis and achieve illegal access to protected images. Furthermore, some specially crafted DNNs may even erase invisible watermarks embedded within the protected images, which eventually leads to the collapse of this protection and certification mechanism. To address these issues, inspired by the adversarial attack, we introduce Invisible Adversarial Watermarking (IAW), a novel security mechanism to enhance the copyright protection efficacy of watermarks. Specifically, we design an Adversarial Watermarking Fusion Model (AWFM) to efficiently generate Invisible Adversarial Watermark Images (IAWIs). By modeling the embedding of watermarks and adversarial perturbations as a unified task, the generated IAWIs can effectively defend against unauthorized identification, access, and erase via DNNs and identify the ownership by extracting the embedded watermark. Experimental results show that the proposed IAW presents superior extraction accuracy, attack ability, and robustness on different DNNs, and the protected images maintain good visual quality, which ensures its effectiveness as an image protection mechanism.
Förderung
- National Natural Science Foundation of China
- Zhongyuan Science and Technology Innovation Leading Talent Project of China
- Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness
- Graduate Student Scientific Research Innovation Projects of Jiangsu Province
- Open Project the State Key Laboratory of Tibetan Intelligent Information Processing and Application and Key Laboratory
- Open Project Fund of Shandong Provincial Key Laboratory of Computer Network
Zitieren
APA
Wang, J., Wang, H., Zhang, J., Wu, H., Luo, X., & Ma, B. (2025). Invisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(2), 1-22. https://doi.org/10.1145/3652608
Vancouver
Wang J, Wang H, Zhang J, Wu H, Luo X, Ma B. Invisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(2):1-22. doi:10.1145/3652608
BibTeX
@article{Wang2025,
author = {Wang, Jinwei and Wang, Haihua and Zhang, Jiawei and Wu, Hao and Luo, Xiangyang and Ma, Bin},
title = {Invisible Adversarial Watermarking: A Novel Security Mechanism for Enhancing Copyright Protection},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {2},
pages = {1--22},
doi = {10.1145/3652608}
}
EUVIMED