Research on Digital Watermarking Technology Based on Artificial Intelligence Generated Content Model
DOI:
https://doi.org/10.54691/gmzeeb94Keywords:
AI generated content; Digital watermark; Copyright protection; Concealment; robustness.Abstract
With the rapid development of Generative Artificial Intelligence (AIGC) technology, the creation and dissemination of digital content have entered a new era. However, issues such as copyright protection, security, and traceability of these generated contents are gradually becoming prominent, and effective technological measures are still needed to address them. Digital watermarking technology, as an effective means to solve these problems, has a wide range of application prospects. This study proposes a new digital watermarking algorithm specifically targeting the characteristics of AIGC generated content, aiming to address the shortcomings of existing technologies in terms of concealment, robustness, and security. By comparing and analyzing existing technologies, improvement plans were proposed and optimized and experimentally verified. The experimental results show that the proposed algorithm can effectively improve the copyright protection capability of content while ensuring the concealment of watermarks, and has good application prospects.
Downloads
References
[1] Guo Zhaojun, Li Meiling, Zhou Yangming, etc. Research progress on digital watermarking technology for content models generated by artificial intelligence [J]. Journal of Cyberspace Security Science, 2024,2 (01): 13-39.
[2] Liang Yan. Application of Digital Watermarking Technology in Digital Media Copyright Protection and Optimization [J]. Electronic Technology, 2024, 53 (05): 320-321.
[3] Wang Huibing. Research on Image Watermarking Algorithm Based on Deep Learning [D]. Jiangxi University of Science and Technology, 2024.
[4] Wei Ying. Research on Image Digital Watermarking Based on Generative Adversarial Networks [D]. Chongqing University of Technology, 2022.
[5] Liu Anan, Su Yuting, Wang Lanjun, etc. Progress in AIGC Visual Content Generation and Traceability Research [J]. Chinese Journal of Image and Graphics, 2024, 29 (06): 1535-1554.
[6] Wang Jie. Research on Copyright Algorithm Based on Adversarial Samples [D]. Dongguan University of Technology, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Humanities and Social Sciences

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.